Triple
T9974317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calvin Johnson |
E196287
|
entity |
| Predicate | sportsTeamTenure |
P8422
|
FINISHED |
| Object | Detroit Lions 2007–2015 |
—
|
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 Lions 2007–2015 | Statement: [Calvin Johnson, sportsTeamTenure, Detroit Lions 2007–2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportsTeamTenure Context triple: [Calvin Johnson, sportsTeamTenure, Detroit Lions 2007–2015]
-
A.
teamTenure
Indicates the duration or length of time an entity has been part of a particular team.
-
B.
nflTeamTenure
chosen
Indicates the period of time that an individual was a member of a specific NFL team.
-
C.
NBAteamTenure
Indicates the period of time during which a player is a member of a specific NBA team.
-
D.
careerSpanTeam
Indicates the team for which an individual’s entire career span (or a defined portion of it) is being measured or associated.
-
E.
winnerCareerSpanTeam
Indicates the team for which a winner competed during the span of their professional career.
- 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_69ca82eea2b88190a0e511d21a31f386 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb849da448190b826cb8fbf2eeb89 |
completed | April 2, 2026, 12:28 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9daa808190b413a1b9a1e929e2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:48 p.m.