Triple
T26957945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Majma'ah Sports City Stadium |
E678958
|
entity |
| Predicate | leagueMatchesHost |
P7477
|
FINISHED |
| Object | Saudi domestic competitions |
—
|
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: Saudi domestic competitions | Statement: [Al Majma'ah Sports City Stadium, leagueMatchesHost, Saudi domestic competitions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leagueMatchesHost Context triple: [Al Majma'ah Sports City Stadium, leagueMatchesHost, Saudi domestic competitions]
-
A.
hostedHomeMatchesFor
Indicates that an entity organized and held competitive matches at its own home venue for another entity or group.
-
B.
leagueMatchesPlayed
Indicates the number of matches an entity has participated in within a specific league competition.
-
C.
involvesLeagueMatches
Indicates that the described context, event, or competition includes or is composed of league matches.
-
D.
hostsLeague
chosen
Indicates that one entity serves as the organizing or venue-providing host for a particular league.
-
E.
topDivisionMatchesHosted
Indicates that an entity has hosted matches in the highest-level division of a competition or league.
- 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_69eeeb4e75f08190b14fc91ca4a91488 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c1f94ac8190bc6fbc7916fc0d82 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 6:28 a.m.