Triple
T4642784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Churchill Downs |
E101692
|
entity |
| Predicate | firstKentuckyDerbyHeld |
P6638
|
FINISHED |
| Object | 1875 |
—
|
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: 1875 | Statement: [Churchill Downs, firstKentuckyDerbyHeld, 1875]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstKentuckyDerbyHeld Context triple: [Churchill Downs, firstKentuckyDerbyHeld, 1875]
-
A.
firstTourDeFranceHeld
Indicates that the subject is the location or context in which the first Tour de France event was held.
-
B.
firstEditionHeldIn
chosen
Indicates the location where the first edition or initial occurrence of an event was held.
-
C.
notableDerbyHosted
Indicates that an entity has hosted a derby event considered notable or significant.
-
D.
isFirstWorldCupHeldIn
Indicates that a country's first participation in the FIFA World Cup took place in the specified host nation or location.
-
E.
firstCeremony
Indicates that an entity participates in or is associated with the earliest or initial ceremony in a sequence or context.
- 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_69bd43d3bc7c81908f81fcf380476b0f |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a93047c8190990c94fd5a57c867 |
completed | March 20, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69bd5234d24c819095c79890b70eff9a |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:14 p.m.