Triple
T9774926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crusaders |
E237221
|
entity |
| Predicate | homeCountryTeamOf |
P90576
|
FINISHED |
| Object | Christchurch rugby supporters |
—
|
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: Christchurch rugby supporters | Statement: [Crusaders, homeCountryTeamOf, Christchurch rugby supporters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCountryTeamOf Context triple: [Crusaders, homeCountryTeamOf, Christchurch rugby supporters]
-
A.
countryOfTeam
Indicates that a team is associated with or represents a particular country.
-
B.
homeCountryTeamMatches
Indicates that the matches involve the team representing its own home country.
-
C.
team2Country
Indicates that a given team is associated with or represents a particular country.
-
D.
hadTeamFromCountry
Indicates that an entity (such as an event, league, or competition) included or was associated with at least one team originating from a specified country.
-
E.
homeCountryFIFA_code
Indicates the FIFA country code that represents the national association or home country with which an entity is affiliated.
- F. None of above. chosen
Provenance (4 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_69ca84d975a08190aab25b02a89bdab3 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda13148288190bcbb3b4a066d9fc1 |
completed | April 1, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69cd03d3b68c81909e570401a891b9f2 |
completed | April 1, 2026, 11:38 a.m. |
| PDg | Predicate description generation | batch_69cd06aa8bc88190904be19c8953def8 |
completed | April 1, 2026, 11:51 a.m. |
Created at: March 30, 2026, 8:26 p.m.