Triple
T25446388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bharat Dynamics Limited |
E637647
|
entity |
| Predicate | keyClient |
P158527
|
FINISHED |
| Object | Ministry of Defence (India) |
—
|
NE NERFINISHED |
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: Ministry of Defence (India) | Statement: [Bharat Dynamics Limited, keyClient, Ministry of Defence (India)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyClient Context triple: [Bharat Dynamics Limited, keyClient, Ministry of Defence (India)]
-
A.
keyHub
Indicates a central or primary element that connects, coordinates, or controls multiple related components or interactions.
-
B.
keyCenter
Indicates the central or primary tonal focus around which other related elements are organized or interpreted.
-
C.
keyUse
Indicates that one entity is used as a key or means of access, control, or identification for another entity.
-
D.
keyMaterial
Indicates that an entity serves as cryptographic key material used to secure, encrypt, or authenticate data in a security-related relationship.
-
E.
keyClass
Indicates that one class functions as the primary or identifying class associated with another entity or structure.
- F. None of above. chosen
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_69e75db7c5048190b8da9cd7eeedb610 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f70455f48190b23c09dbed884015 |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
| PDg | Predicate description generation | batch_69f46d361c348190b5fdfd805ecde01b |
completed | May 1, 2026, 9:07 a.m. |
Created at: April 21, 2026, 2:02 p.m.