Triple
T18044760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secretariat |
E431742
|
entity |
| Predicate | BelmontStakesMarginOfVictory |
P129595
|
FINISHED |
| Object | 31 lengths |
—
|
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: 31 lengths | Statement: [Secretariat, BelmontStakesMarginOfVictory, 31 lengths]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BelmontStakesMarginOfVictory Context triple: [Secretariat, BelmontStakesMarginOfVictory, 31 lengths]
-
A.
mostSuccessfulHorse
Indicates that the subject is the horse with the greatest level of success (e.g., wins, earnings, or titles) within a specified group or context.
-
B.
notableRaceTrackDepicted
Indicates that a work or representation depicts a race track that is considered notable or significant.
-
C.
secretariat
Indicates that an entity serves as an administrative office or coordinating body (a secretariat) responsible for managing and supporting the activities of an organization or group.
-
D.
winnerLane
Indicates that a particular lane is the one in which the winner of a race or competition is located.
-
E.
raceWon
Indicates that one participant has achieved victory in a race or competitive event over others.
- 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_69d8b906482481908183315b9ecf9994 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4bff13f488190993445769551c9c2 |
completed | April 19, 2026, 11:43 a.m. |
| PD | Predicate disambiguation | batch_69e3f908da508190a088aa837ea5b7af |
completed | April 18, 2026, 9:35 p.m. |
| PDg | Predicate description generation | batch_69e42d8eefa88190a700c7c1b4213e46 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:25 a.m.