Triple
T9417182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carl Eller |
E227054
|
entity |
| Predicate | NFL100AllTimeTeamMember |
P89037
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Carl Eller, NFL100AllTimeTeamMember, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NFL100AllTimeTeamMember Context triple: [Carl Eller, NFL100AllTimeTeamMember, true]
-
A.
ProFootballHallOfFame
Indicates that a person has been inducted into the Pro Football Hall of Fame.
-
B.
SuperBowlChampionAsPlayerWith
Indicates that one entity was a Super Bowl champion as a player in association with the other entity (such as a team, season, or organization).
-
C.
proFootballHallOfFameTeam
Indicates that a team is associated with the Pro Football Hall of Fame, typically by having players, coaches, or contributors inducted.
-
D.
NFLTeamAchievement
Indicates that an NFL team has attained a specific accomplishment, milestone, or honor within professional football competition.
-
E.
nflAllTimePointsLeader
Indicates that the subject is the player who holds the record for the most career points scored in NFL history.
- 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_69ca84359e7c819091148ba4b670e436 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd68cb4be08190a47f901a9703f9db |
completed | April 1, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69cca54c37f88190bddccf28e5fe5c84 |
completed | April 1, 2026, 4:55 a.m. |
| PDg | Predicate description generation | batch_69cca9d07eb08190866eb15333386dfa |
completed | April 1, 2026, 5:14 a.m. |
Created at: March 30, 2026, 7:48 p.m.