Triple
T28004044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Brigade |
E707224
|
entity |
| Predicate | homeCityOfClubSupported |
P164554
|
FINISHED |
| Object | Glasgow |
—
|
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: Glasgow | Statement: [Green Brigade, homeCityOfClubSupported, Glasgow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCityOfClubSupported Context triple: [Green Brigade, homeCityOfClubSupported, Glasgow]
-
A.
usedByClubFromCity
Indicates that something (such as a facility, stadium, or resource) is utilized by a sports club that is based in a particular city.
-
B.
homeCountryOfClubSupported
Indicates the country that is the home nation of the club a person (or entity) supports.
-
C.
participatingClubsFromCity
Indicates that the clubs involved in an event or activity originate from or are based in a specified city.
-
D.
isLocatedInCityWithClub
Indicates that an entity is situated in a city that has at least one (sports or similar) club based there.
-
E.
hasHomeClub
Indicates that an entity (typically a person, such as an athlete) is associated with a particular club as their primary or official home organization.
- 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_69ef96ba350c81908230d0b501b974c4 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f64e6e8c9081908ce4d364aa26147a |
completed | May 2, 2026, 7:20 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f64db8ee1881909362701d72ffe282 |
completed | May 2, 2026, 7:17 p.m. |
Created at: April 27, 2026, 7:59 p.m.