Triple
T6801410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poincaré duality |
E156194
|
entity |
| Predicate | holdsWithCoefficients |
P73087
|
FINISHED |
| Object | field coefficients |
—
|
LITERAL 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: field coefficients | Statement: [Poincaré duality, holdsWithCoefficients, field coefficients]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsWithCoefficients Context triple: [Poincaré duality, holdsWithCoefficients, field coefficients]
-
A.
holdingType
Indicates the type or category of a holding or possession that one entity has in relation to another or to an asset.
-
B.
holdsIn
Indicates that a relationship, condition, or event is valid or occurs within a specified time interval or temporal context.
-
C.
heldAs
Indicates that one entity is kept, maintained, or regarded in a particular state, role, or condition by another entity.
-
D.
heldMany
Indicates that one entity has possessed or maintained control over a large number or quantity of another entity over time.
-
E.
holdsFor
Indicates that a particular relationship or condition remains true over a specified interval or duration of time.
- 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_69c68826e6a48190a3d220b541e639de |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2e595188190a0bb4b595df3adb2 |
completed | March 27, 2026, 6:56 p.m. |
| PD | Predicate disambiguation | batch_69c6d099bf08819089a9f9894d037e74 |
completed | March 27, 2026, 6:46 p.m. |
| PDg | Predicate description generation | batch_69c6d2a8f9188190abbb8c730e7b5edf |
completed | March 27, 2026, 6:55 p.m. |
Created at: March 27, 2026, 2:16 p.m.