Triple
T13464249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London (during Arsenal career) |
E311453
|
entity |
| Predicate | stadiumCapacityApproximate |
P13599
|
FINISHED |
| Object | 38000 at Highbury in later years |
—
|
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: 38000 at Highbury in later years | Statement: [London (during Arsenal career), stadiumCapacityApproximate, 38000 at Highbury in later years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stadiumCapacityApproximate Context triple: [London (during Arsenal career), stadiumCapacityApproximate, 38000 at Highbury in later years]
-
A.
stadiumCapacityApprox
chosen
Indicates an approximate number of people that a stadium can accommodate.
-
B.
homeStadiumCapacity
Indicates the seating capacity of the stadium that serves as a team's or organization's home venue.
-
C.
stadiumCapacityContext
Indicates the seating capacity of a stadium as it applies within a specific contextual scope (such as time, event, or configuration).
-
D.
formerStadiumCapacityApprox
Indicates that an entity’s past stadium capacity is approximately equal to the given number, rather than an exact figure.
-
E.
venueCapacityApproximate
Indicates an approximate or estimated capacity of a venue in terms of how many people it can accommodate.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf0f1830819085700b4521e44678 |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69dbadfddefc81909ef7fde23b181b5c |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:41 p.m.