Triple
T14538010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1935–36 NHL season |
E341098
|
entity |
| Predicate | longestGameFinalScore |
P30626
|
FINISHED |
| Object | 1–0 Detroit Red Wings |
—
|
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: 1–0 Detroit Red Wings | Statement: [1935–36 NHL season, longestGameFinalScore, 1–0 Detroit Red Wings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: longestGameFinalScore Context triple: [1935–36 NHL season, longestGameFinalScore, 1–0 Detroit Red Wings]
-
A.
mostGoalsInSingleGameDate
Indicates the date on which an entity achieved its highest number of goals scored in a single game.
-
B.
opponentFinalScore
chosen
Indicates the final score achieved by an opposing participant or team in a contest or game.
-
C.
worldCupFinalScore
Indicates the final score outcome of a FIFA World Cup match, typically specifying the number of goals each team scored by the end of the final game.
-
D.
finalScore90Minutes
Indicates the final score of a match after the standard 90 minutes of regular playing time, excluding any extra time or penalty shootouts.
-
E.
championshipGameScore
Indicates the final score achieved by each participant in a championship 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_69d822dac79c8190a84a073f3cbaced5 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb1bb90008190947ac0961393446d |
completed | April 14, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69de5c546c7081909e27d504ec360c5c |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:22 a.m.