Triple
T27143701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mares’ Hurdle |
E681881
|
entity |
| Predicate | raceGradeAtInauguration |
P161893
|
FINISHED |
| Object | Grade 2 |
—
|
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: Grade 2 | Statement: [Mares’ Hurdle, raceGradeAtInauguration, Grade 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceGradeAtInauguration Context triple: [Mares’ Hurdle, raceGradeAtInauguration, Grade 2]
-
A.
positionInauguratedIn
Indicates that a person officially assumed a particular position or office at a specified time or event of inauguration.
-
B.
inaugurationYear
Indicates the calendar year in which an entity was formally inaugurated or officially brought into operation.
-
C.
isInauguralElectionFor
Indicates that an election is the first (inaugural) occurrence held for a particular office, position, or governing body.
-
D.
inauguralClassYear
Indicates the year in which the first (inaugural) class or cohort associated with an entity began or was established.
-
E.
ordinalPresidentInaugurated
Indicates the ordinal position of a person in the sequence of presidents who have been officially inaugurated.
- 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_69eefacca3888190b67238d380e8f28b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f624c3e4bc8190af9a5d9b3c30d117 |
completed | May 2, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
| PDg | Predicate description generation | batch_69f61fa35ac48190890102c348ed81a0 |
completed | May 2, 2026, 4 p.m. |
Created at: April 27, 2026, 9:10 a.m.