Triple
T18320644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2007 American Horse of the Year |
E438867
|
entity |
| Predicate | winnerColor |
P131371
|
FINISHED |
| Object | chestnut |
—
|
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: chestnut | Statement: [2007 American Horse of the Year, winnerColor, chestnut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerColor Context triple: [2007 American Horse of the Year, winnerColor, chestnut]
-
A.
winnerState
Indicates the state or condition of an entity that has achieved victory or been declared the winner in a given context.
-
B.
winnerBackground
Indicates the background or prior circumstances associated with the entity that has won a contest, competition, or selection.
-
C.
winnerRight
Indicates that the referenced entity is the winner on the right side or right position in a competitive or comparative context.
-
D.
winnerType
Indicates the category or kind of winner associated with an event, competition, or outcome.
-
E.
winnerAssociated
Indicates that there is a relevant connection or affiliation between a winner and another entity in the context of a particular event or competition.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa5a3508190a3025e71c11d79e2 |
completed | April 19, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
| PDg | Predicate description generation | batch_69e451a0ba208190a5fe92832a8f7a49 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 10:36 a.m.