Triple
T3595751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Hostetler |
E76135
|
entity |
| Predicate | tookOverAsStarter |
P8877
|
FINISHED |
| Object | 1990 NFL season |
—
|
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: 1990 NFL season | Statement: [Jeff Hostetler, tookOverAsStarter, 1990 NFL season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tookOverAsStarter Context triple: [Jeff Hostetler, tookOverAsStarter, 1990 NFL season]
-
A.
takesOver
chosen
Indicates that one entity assumes control, ownership, or responsibility for another entity, often replacing its previous controller.
-
B.
tookPositionOn
Indicates that an entity expressed or adopted a specific stance, opinion, or viewpoint regarding a particular issue, topic, or subject.
-
C.
cameToPowerAfter
Indicates that one entity assumed authority or control following the rule or tenure of another entity.
-
D.
tookHeadOf
Indicates that one entity removed or claimed the head (literal or symbolic) of another entity.
-
E.
successorAsPretender
Indicates that one entity becomes the next claimant or would-be holder of a title, position, or throne after another, without necessarily being officially recognized.
- 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_69ad85d8042081908af94a04c410dec0 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc15f41cc819085b3e897d823757d |
completed | March 8, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69adb83b66708190bb9d2f23d6fd308e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:22 p.m.