Triple
T24681054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NAC Breda |
E611129
|
entity |
| Predicate | hasRegionalDerby |
P52081
|
FINISHED |
| Object | Derby with Willem II |
—
|
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: Derby with Willem II | Statement: [NAC Breda, hasRegionalDerby, Derby with Willem II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRegionalDerby Context triple: [NAC Breda, hasRegionalDerby, Derby with Willem II]
-
A.
hasHomeDerbyFor
Indicates that one entity serves as the home venue or location where another entity’s derby event is held.
-
B.
countryOfRivalry
Indicates that one entity is a country with which another entity has a relationship of rivalry or adversarial competition.
-
C.
regionDerby
chosen
Indicates a competitive match or rivalry that takes place between teams or participants from the same geographic region.
-
D.
isFromCityWithDerby
Indicates that an entity originates from a city that has a football (or sports) derby with another team from the same city.
-
E.
hasLocalRivalry
Indicates that there is an ongoing competitive or adversarial relationship between entities that are geographically close or share the same local area.
- 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_69e2c4d5c2dc8190ac857dea25ec6ce9 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
Created at: April 18, 2026, 3:10 a.m.