Triple
T22092348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parker |
E545941
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Parker |
—
|
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: Parker | Statement: [Parker, character, Parker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parker Context triple: [Parker, character, Parker]
-
A.
Parker
Parker is a suburban town in Colorado located along the eastern edge of the Denver metropolitan area.
-
B.
Parker
Parker is the troubled, tattoo-obsessed protagonist of Flannery O’Connor’s short story “Parker’s Back,” whose spiritual and personal turmoil drive the narrative.
-
C.
Parker
Parker is a company that operates as a subsidiary under the ownership of Sanford.
-
D.
Parker
Parker is a character associated with the IYS Insurance brand, likely featured in its marketing or promotional materials.
-
E.
Parker
chosen
Parker is a skilled, eccentric thief and infiltration specialist from the TV series "Leverage," known for her acrobatics, social awkwardness, and central role on the Leverage team.
- 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e6b1d881909bf0f4a52199354c |
completed | April 28, 2026, 9:38 p.m. |
Created at: April 16, 2026, 8:29 p.m.