Triple
T28004046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Brigade |
E707224
|
entity |
| Predicate | clubSupportedFullName |
P76025
|
FINISHED |
| Object | Celtic Football Club |
—
|
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: Celtic Football Club | Statement: [Green Brigade, clubSupportedFullName, Celtic Football Club]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clubSupportedFullName Context triple: [Green Brigade, clubSupportedFullName, Celtic Football Club]
-
A.
clubFullNameSupported
Indicates that the complete official name of a club is recognized and supported within the system.
-
B.
clubFullName
Indicates the complete official name of a club as opposed to an abbreviation or short form.
-
C.
supportsClubFullName
chosen
Indicates that one entity provides backing, endorsement, or assistance to a sports club identified by its full official name.
-
D.
associatedClubCommonName
Indicates that there is a relationship linking an entity to the commonly used or popular name of a club with which it is associated.
-
E.
associatedClubShortName
Indicates that there is a relationship linking an entity to the abbreviated or short name of a club with which it is associated.
- 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_69ef96ba350c81908230d0b501b974c4 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63fd79e4c8190af9263b679e5ff07 |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 7:59 p.m.