Triple
T15338095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheltenham Gold Cup |
E366719
|
entity |
| Predicate | raceFor |
P19141
|
FINISHED |
| Object | thoroughbred racehorses |
—
|
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: thoroughbred racehorses | Statement: [Cheltenham Gold Cup, raceFor, thoroughbred racehorses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceFor Context triple: [Cheltenham Gold Cup, raceFor, thoroughbred racehorses]
-
A.
racesAgainst
Indicates that one entity competes in a race directly against another entity.
-
B.
partyRaceContext
Indicates the contextual relationship between a party and a race, such as how a political party is involved in, associated with, or positioned within a particular electoral race.
-
C.
raceWon
Indicates that one participant has achieved victory in a race or competitive event over others.
-
D.
raceMeeting
chosen
Indicates a competitive event where multiple participants race against each other under shared rules and conditions.
-
E.
runnerUp
Indicates that one entity finished in second place relative to another in a competition or ranking.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e11b22c81908280efe65acd5454 |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:17 a.m.