Triple
T26325541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steel Authority of India Limited |
E662240
|
entity |
| Predicate | keyProductUser |
P93351
|
FINISHED |
| Object | Indian Railways |
E100843
|
NE FINISHED |
How this triple was built (2 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: Indian Railways | Statement: [Steel Authority of India Limited, keyProductUser, Indian Railways]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyProductUser Context triple: [Steel Authority of India Limited, keyProductUser, Indian Railways]
-
A.
keyProductRole
Indicates that an entity serves as a primary or central product in relation to another entity, defining its main product role in that context.
-
B.
hasProductUser
chosen
Indicates that a product is associated with or used by a particular user.
-
C.
keyProvision
Indicates that one entity serves as a primary or essential provision, resource, or supply for another entity.
-
D.
keyUse
Indicates that one entity is used as a key or means of access, control, or identification for another entity.
-
E.
keyCustom
Indicates that something has a user-defined or non-standard key used for identification, access, or configuration.
- F. None of above.
Provenance (4 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_69ee812f32748190871d970c4e2a8ddf |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60f2fec2c8190a0271e3256f22be6 |
completed | May 2, 2026, 2:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a118fb4707c81909810d08922c242f8 |
completed | May 23, 2026, 11:29 a.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:30 p.m.