Triple
T22147297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Five-Year Plan of India |
E547319
|
entity |
| Predicate | economicModel |
P252
|
FINISHED |
| Object |
Mahalanobis model
The Mahalanobis model is an economic planning framework that emphasizes rapid industrialization through heavy industry and capital goods, heavily influencing India’s early Five-Year Plans.
|
E1521492
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mahalanobis model | Statement: [Second Five-Year Plan of India, economicModel, Mahalanobis model]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mahalanobis model Context triple: [Second Five-Year Plan of India, economicModel, Mahalanobis model]
-
A.
Mahalanobis distance
Mahalanobis distance is a multivariate measure of the distance between a point and a distribution (or between distributions) that accounts for correlations between variables via the covariance matrix.
-
B.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
C.
Gaussian mixture models
Gaussian mixture models are probabilistic clustering models that represent data as a combination of multiple Gaussian distributions, allowing soft cluster assignments and more flexible cluster shapes than KMeans.
-
D.
Bayesian model averaging
Bayesian model averaging is a statistical technique that combines predictions from multiple models by weighting them according to their posterior probabilities to account for model uncertainty.
-
E.
Tobit model
The Tobit model is an econometric regression model designed for situations where the dependent variable is censored, allowing consistent estimation when observations are only partially observed beyond certain limits.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mahalanobis model Triple: [Second Five-Year Plan of India, economicModel, Mahalanobis model]
Generated description
The Mahalanobis model is an economic planning framework that emphasizes rapid industrialization through heavy industry and capital goods, heavily influencing India’s early Five-Year Plans.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mahalanobis model Target entity description: The Mahalanobis model is an economic planning framework that emphasizes rapid industrialization through heavy industry and capital goods, heavily influencing India’s early Five-Year Plans.
-
A.
Mahalanobis distance
Mahalanobis distance is a multivariate measure of the distance between a point and a distribution (or between distributions) that accounts for correlations between variables via the covariance matrix.
-
B.
Hotelling’s T-squared distribution
Hotelling’s T-squared distribution is a multivariate generalization of Student’s t-distribution used primarily for hypothesis testing and constructing confidence regions for mean vectors in multivariate statistics.
-
C.
Gaussian mixture models
Gaussian mixture models are probabilistic clustering models that represent data as a combination of multiple Gaussian distributions, allowing soft cluster assignments and more flexible cluster shapes than KMeans.
-
D.
Bayesian model averaging
Bayesian model averaging is a statistical technique that combines predictions from multiple models by weighting them according to their posterior probabilities to account for model uncertainty.
-
E.
Tobit model
The Tobit model is an econometric regression model designed for situations where the dependent variable is censored, allowing consistent estimation when observations are only partially observed beyond certain limits.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f156988190bc9a24a37418e849 |
completed | April 28, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a9702ed508190ac4db27c3dc46879 |
completed | May 18, 2026, 4:35 a.m. |
| NEDg | Description generation | batch_6a0a97bd6fe081909a3e609ff2022f82 |
completed | May 18, 2026, 4:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a9843fb3481908a120dc3ac360124 |
completed | May 18, 2026, 4:40 a.m. |
Created at: April 16, 2026, 8:33 p.m.