Triple
T20425432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carrickmines |
E500986
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Leopardstown |
—
|
NE NERFINISHED |
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: Leopardstown | Statement: [Carrickmines, near, Leopardstown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leopardstown Context triple: [Carrickmines, near, Leopardstown]
-
A.
Leopardstown
chosen
Leopardstown is a suburban area in south Dublin, Ireland, best known for its major horse racing venue, Leopardstown Racecourse.
-
B.
Navan Racecourse
Navan Racecourse is a prominent horse racing venue in Navan, County Meath, Ireland, known for hosting both National Hunt and flat racing events.
-
C.
The Curragh racecourse
The Curragh racecourse is Ireland’s most prestigious flat horse racing venue, renowned for hosting classic races such as the Irish Derby.
-
D.
Fairyhouse Racecourse
Fairyhouse Racecourse is a prominent Irish horse racing venue in County Meath, best known for hosting major National Hunt events such as the Irish Grand National.
-
E.
Naas Racecourse
Naas Racecourse is a prominent Irish horse racing venue located near the town of Naas in County Kildare, hosting both flat and National Hunt meetings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4aa68fc8190b1a14c55575ef04a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67ba7afa4819095c9b75fab3cbbfc |
completed | April 20, 2026, 7:16 p.m. |
Created at: April 16, 2026, 11:30 a.m.