Triple
T24651929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISO 3166-2:HT |
E610271
|
entity |
| Predicate | subdivisionNameExample |
P157663
|
FINISHED |
| Object |
Nord
Nord is a department in northern Haiti known for its capital Cap-Haïtien and its historical sites, including the Citadelle Laferrière.
|
E1645765
|
NE FINISHED |
How this triple was built (3 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: Nord | Statement: [ISO 3166-2:HT, subdivisionNameExample, Nord]
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: Nord Triple: [ISO 3166-2:HT, subdivisionNameExample, Nord]
Generated description
Nord is a department in northern Haiti known for its capital Cap-Haïtien and its historical sites, including the Citadelle Laferrière.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subdivisionNameExample Context triple: [ISO 3166-2:HT, subdivisionNameExample, Nord]
-
A.
subdivisionNameExample
chosen
Indicates that the predicate provides an example name of a subdivision (such as a district, region, or administrative area) associated with an entity.
-
B.
subdivisionNameType
Indicates the type or category of a named geographic or administrative subdivision (e.g., province, state, district) associated with an entity.
-
C.
subdivisionName0
Indicates the name assigned to the first (primary) subdivision or sub-unit associated with an entity.
-
D.
subdivisionName1
Indicates that the first named subdivision is identified by a specific name or designation within a larger geographic or organizational hierarchy.
-
E.
subdivisionNameLocal
Indicates the locally used or native-language name assigned to a specific administrative or geographic subdivision.
- F. None of above.
Provenance (6 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_69e2c4d350a481909170482bc2ce6af9 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a10049ac3a481909fc8eae6b8f9cdf8 |
completed | May 22, 2026, 7:24 a.m. |
| NEDg | Description generation | batch_6a10095d986881909082cc5a32b6d56e |
completed | May 22, 2026, 7:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1009d311b08190acf35a3ed552b9c1 |
completed | May 22, 2026, 7:46 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 2:34 a.m.