Triple
T13381980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahmed bin Ali Stadium |
E319339
|
entity |
| Predicate | capacityAfterTournament |
P109704
|
FINISHED |
| Object | about 21000 |
—
|
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: about 21000 | Statement: [Ahmed bin Ali Stadium, capacityAfterTournament, about 21000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capacityAfterTournament Context triple: [Ahmed bin Ali Stadium, capacityAfterTournament, about 21000]
-
A.
finalTournamentSlotsVariesByEdition
Indicates that the number or allocation of final tournament slots changes depending on the specific edition of the competition.
-
B.
numberOfFinalTournamentTeams
Indicates the total count of teams that participate in the final stage of a tournament.
-
C.
numberOfKnockouts
Indicates the total count of times an entity has defeated opponents by knockout.
-
D.
qualifiedForTournament
Indicates that an entity meets the necessary criteria or requirements to participate in a particular tournament.
-
E.
numberOfTournaments
Indicates the total count of tournaments associated with or participated in by an entity.
- 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_69d806b886bc8190b676e7768b8e01c5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dadce694788190881d1feac5b75720 |
completed | April 11, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69d9a03189908190a784a2755f8d81e1 |
completed | April 11, 2026, 1:13 a.m. |
| PDg | Predicate description generation | batch_69dadcce5a808190847f2a7833b67a5a |
completed | April 11, 2026, 11:44 p.m. |
Created at: April 9, 2026, 9:33 p.m.