Triple
T23725903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bourbon fleur-de-lis |
E586272
|
entity |
| Predicate | typicallyOnField |
P121570
|
FINISHED |
| Object | blue |
—
|
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: blue | Statement: [Bourbon fleur-de-lis, typicallyOnField, blue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyOnField Context triple: [Bourbon fleur-de-lis, typicallyOnField, blue]
-
A.
centeredOnField
Indicates that one entity is positioned or focused around the central area of a specified field or domain.
-
B.
locationOnField
chosen
Indicates the specific position or area that an entity occupies on a defined field or playing surface.
-
C.
coversField
Indicates that one entity extends over, protects, or occupies the surface or area of a field associated with another entity.
-
D.
possibleField
Indicates that an entity may be associated with, or located within, a particular field or domain, but this association is not certain or exclusive.
-
E.
rulingOnField
Indicates a decision or judgment made regarding a specific field, domain, or area of concern.
- F. None of above.
Provenance (3 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b915a888819088e92f99711e8120 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:08 p.m.