Triple
T14538008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1935–36 NHL season |
E341098
|
entity |
| Predicate | longestGameTeams |
P114841
|
FINISHED |
| Object | Detroit Red Wings vs Montreal Maroons |
—
|
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: Detroit Red Wings vs Montreal Maroons | Statement: [1935–36 NHL season, longestGameTeams, Detroit Red Wings vs Montreal Maroons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: longestGameTeams Context triple: [1935–36 NHL season, longestGameTeams, Detroit Red Wings vs Montreal Maroons]
-
A.
teamWithMostGames
Indicates the relationship where a team is identified as the one that has played the highest number of games within a given set or context.
-
B.
mostAwardsHolderTeam
Indicates the team that holds the highest number of awards within a given set or competition.
-
C.
mostGamesWonBy
Indicates that one entity holds the record for having won the greatest number of games compared to others in a given context.
-
D.
mostGoalsInSingleGameOpponent
Indicates the opposing team against which an entity scored its highest number of goals in a single game.
-
E.
consecutiveGamesRecordHeldUntil
Indicates that an entity held the record for most consecutive games until a specified later point in time or event.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69de610330a48190b558235a14c0dc9f |
completed | April 14, 2026, 3:45 p.m. |
Created at: April 10, 2026, 1:22 a.m.