Triple
T18110987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ascot Gold Cup |
E433471
|
entity |
| Predicate | recordHolders |
P29425
|
FINISHED |
| Object | Yeats – four wins |
—
|
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: Yeats – four wins | Statement: [Ascot Gold Cup, recordHolders, Yeats – four wins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordHolders Context triple: [Ascot Gold Cup, recordHolders, Yeats – four wins]
-
A.
worldRecordsHeld
Indicates that an entity holds or has achieved one or more officially recognized world records.
-
B.
worldRecordSet
Indicates that an entity has achieved and established the best performance ever recorded in the world for a particular activity, event, or measurable criterion.
-
C.
isAllTimeRecordHolderFor
chosen
Indicates that an entity holds the highest or best performance record of all time for a particular category, event, or metric.
-
D.
previousRecordHolder
Indicates that one entity was the former holder of a particular record before another entity surpassed or replaced it.
-
E.
recordHolderMen
Indicates that the subject is the male athlete who holds the record for a specified event or category.
- 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddd2038081909515fb6d17495cbf |
completed | April 19, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_69e43313ca788190baa224269e71de49 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:28 a.m.