Triple
T1725530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Riggs |
E37486
|
entity |
| Predicate | matchOutcome |
P10213
|
FINISHED |
| Object | lost to Billie Jean King in straight sets |
—
|
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: lost to Billie Jean King in straight sets | Statement: [Bobby Riggs, matchOutcome, lost to Billie Jean King in straight sets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchOutcome Context triple: [Bobby Riggs, matchOutcome, lost to Billie Jean King in straight sets]
-
A.
gameOutcome
chosen
Indicates the result or final status of a game, such as which side won, lost, or if it ended in a draw.
-
B.
finalMatchType
Indicates the specific category or format of the concluding or decisive match in a series or competition.
-
C.
tacticalOutcome
Indicates the specific result or consequence produced by a particular tactic or tactical action in a given situation.
-
D.
outcomeType
Indicates the specific category or nature of the result produced by an event, process, or action.
-
E.
subsequentOutcomeForWinner
Indicates that the predicate links a winner to an outcome or event that occurs to or for them after their initial victory.
- 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_69a8861acab88190bb43cde203429399 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aadb7bda1081908f2c41c520c9c55c |
completed | March 6, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69aa61c0a0288190bce9d60062a84b69 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.