Triple
T10120202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Cup |
E223266
|
entity |
| Predicate | teamMatchFormat |
P78540
|
FINISHED |
| Object | best of five matches |
—
|
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: best of five matches | Statement: [Thomas Cup, teamMatchFormat, best of five matches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamMatchFormat Context triple: [Thomas Cup, teamMatchFormat, best of five matches]
-
A.
conferenceMatchupType
Indicates the type or category of matchup between entities within a conference context (e.g., intra-conference vs. inter-conference).
-
B.
teamFormat
chosen
Indicates the structural arrangement or configuration in which a team is organized or operates.
-
C.
hasRivalryFormat
Indicates that there is a specific structure, set of rules, or format that defines how a rivalry between entities is conducted or organized.
-
D.
tourFormat
Indicates the specific structure, style, or type of a tour associated with an entity.
-
E.
playedFormat
Indicates that an entity (such as a game, show, or media content) is or was presented, delivered, or experienced in a particular format (such as digital, physical, live, or specific media type).
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2659cdc8190b3ba91426bda55ec |
completed | April 2, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba1d360819087698d04a53cc87e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.