Triple
T32092661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Argentina defeated France in opening match |
E819636
|
entity |
| Predicate | openingGame |
P23679
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Argentina defeated France in opening match, openingGame, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingGame Context triple: [Argentina defeated France in opening match, openingGame, true]
-
A.
openingGame6
Indicates that an entity participates in or is associated with the sixth game in a series, specifically in the context of its opening or initial phase.
-
B.
openingRace
Indicates that one race serves as the initial or first event in a sequence of races or a racing competition.
-
C.
openingMatch
chosen
Indicates that one entity serves as the initial or first match, game, or contest in a series, event, or competition involving another entity.
-
D.
openingPractice
Indicates the practice or rehearsal of opening moves, procedures, or initial actions in a given context.
-
E.
openingConcept
Indicates that one concept serves as the initial or introductory element in relation to another concept, such as the first idea, section, or phase in a sequence or structure.
- 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_69f349004b2481908ce2e50af0d579a8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7817daf00819098936402e75ab0a6 |
completed | May 3, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f780fc5ed88190b7200ee5a29940af |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 1, 2026, 12:25 a.m.