Triple
T19923692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paxton Road Stand |
E478867
|
entity |
| Predicate | homeSupporterSection |
P42456
|
FINISHED |
| Object | Tottenham Hotspur fans |
—
|
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: Tottenham Hotspur fans | Statement: [Paxton Road Stand, homeSupporterSection, Tottenham Hotspur fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeSupporterSection Context triple: [Paxton Road Stand, homeSupporterSection, Tottenham Hotspur fans]
-
A.
homeSupportersSectionFor
chosen
Indicates that a particular seating section is designated for the home team's supporters at a sporting event or venue.
-
B.
homeSection
Indicates that something belongs to, is part of, or is designated as the primary/home section within a larger structure or collection.
-
C.
addressingSupport
Indicates that one entity provides assistance or resources to help another entity address or resolve a specific issue, need, or challenge.
-
D.
homeSectionName
Indicates the designated name or label assigned to a particular section of a home or homepage.
-
E.
supportArea
Indicates that one entity serves as a supporting region or surface that provides structural or functional backing for another entity.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c7be948190a65a1c78ba68dff3 |
completed | April 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.