Triple
T17029839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal County Down Golf Club |
E413162
|
entity |
| Predicate | holesOnChampionshipCourse |
P8596
|
FINISHED |
| Object | 18 |
—
|
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: 18 | Statement: [Royal County Down Golf Club, holesOnChampionshipCourse, 18]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holesOnChampionshipCourse Context triple: [Royal County Down Golf Club, holesOnChampionshipCourse, 18]
-
A.
estimatedHolesInOne
Indicates that a numerical estimate is being made of how many holes-in-one (aces) are expected to occur in a given golf context (such as for a player, round, event, or time period).
-
B.
numberOfGolfCourses
Indicates the total count of golf courses associated with a given entity.
-
C.
hasWaterHazards
Indicates that the subject contains or is associated with one or more water-based obstacles or danger areas.
-
D.
numberOfHoles
chosen
Indicates the count of holes associated with or present in a given entity.
-
E.
hasInnerTurfCourse
Indicates that something (typically a race track or stadium) possesses an inner turf course located within its main track or field.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d918ec8190b54c40c2a5e9b6b9 |
completed | April 18, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_69e35d5be7f48190af9db67a1e23850f |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.