Triple
T17896288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susie Essman |
E447439
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Bolt |
—
|
NE NERFINISHED |
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: Bolt | Statement: [Susie Essman, appearedIn, Bolt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bolt Context triple: [Susie Essman, appearedIn, Bolt]
-
A.
Bolt
Bolt is the surname of Usain Bolt, the Jamaican sprinter widely regarded as one of the greatest and fastest athletes in the history of track and field.
-
B.
Bolt
Bolt is a global ride-hailing and mobility platform offering services like car rides, scooters, and food delivery, competing with companies such as Uber.
-
C.
Bolt
Bolt is the energetic mascot of the Winston-Salem Dash minor league baseball team, known for entertaining fans at games with lively antics and crowd interaction.
-
D.
Bolt
Bolt is the athletic mascot representing Southeastern Oklahoma State University's sports teams.
-
E.
Bolt
chosen
Bolt is a 2008 animated film from Walt Disney Animation Studios about a TV star dog who believes his fictional superpowers are real and embarks on a cross-country journey to save his owner.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d8045748190a4e8c4684439a96b |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:19 a.m.