Triple
T19275609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gallowgate End |
E482044
|
entity |
| Predicate | hasHomeSupporterSection |
P49935
|
FINISHED |
| Object | Newcastle United singing section |
—
|
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: Newcastle United singing section | Statement: [Gallowgate End, hasHomeSupporterSection, Newcastle United singing section]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHomeSupporterSection Context triple: [Gallowgate End, hasHomeSupporterSection, Newcastle United singing section]
-
A.
hasAwaySupportersSection
Indicates that a venue or stadium includes a designated seating area specifically reserved for supporters of the visiting team.
-
B.
hasHomeSupport
Indicates that an entity receives assistance, backing, or favorable conditions from its home environment or local supporters.
-
C.
hasSupportersSection
chosen
Indicates that something includes a dedicated section or area specifically intended for its supporters.
-
D.
hasSupporter
Indicates that one entity supports, endorses, or backs another entity.
-
E.
hasHome
Indicates that an entity possesses or is associated with a place where it lives or is based.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fbbbdf3481909abb46c71f64106a |
completed | April 20, 2026, 10:11 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:29 p.m.