Triple
T29906470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghana vs United States (2014 FIFA World Cup) |
E759548
|
entity |
| Predicate | minuteOfEqualizingGoal |
P65022
|
FINISHED |
| Object | 82 |
—
|
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: 82 | Statement: [Ghana vs United States (2014 FIFA World Cup), minuteOfEqualizingGoal, 82]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minuteOfEqualizingGoal Context triple: [Ghana vs United States (2014 FIFA World Cup), minuteOfEqualizingGoal, 82]
-
A.
minuteOfGoal
Indicates the specific minute in a match when a particular goal was scored.
-
B.
minuteOfOpeningGoal
Indicates the specific minute in a match when the first (opening) goal is scored.
-
C.
equalisingGoalTeam
Indicates that a team scores a goal which brings the score level with the opposing team.
-
D.
awayTeamEqualiserMinute
chosen
Indicates the minute of the match in which the away team scored the goal that brought the scores level.
-
E.
goldenGoalRuleUsed
Indicates that the outcome of a match or competition was determined using the golden goal rule, where the first score in extra time immediately ends the game.
- 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_69f224600590819085e148a01c056ef6 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67756337881908627f7068dc02d9f |
completed | May 2, 2026, 10:14 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:08 p.m.