Triple
T4710006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Bag Man |
E104484
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Crispin Glover |
E194175
|
NE 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: Crispin Glover | Statement: [The Bag Man, starring, Crispin Glover]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crispin Glover Context triple: [The Bag Man, starring, Crispin Glover]
-
A.
Crispin Glover
chosen
Crispin Glover is an American actor, filmmaker, and author best known for his eccentric screen presence and memorable roles in films such as "Back to the Future" and "River's Edge."
-
B.
Michael Culver
Michael Culver is a British actor known for his character roles in film and television, including appearances in productions such as "A Passage to India" and "The Empire Strikes Back."
-
C.
Corey Feldman
Corey Feldman is an American actor and former child star best known for his roles in 1980s films such as "The Goonies," "Stand by Me," and "The Lost Boys."
-
D.
Nicholas Grodin
Nicholas Grodin is the son of the late American actor and comedian Charles Grodin.
-
E.
Ricky Kirshner
Ricky Kirshner is a prominent American television and live-event producer known for overseeing major broadcasts such as Super Bowl halftime shows and high-profile award ceremonies.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd43eac3c08190af7e4020c6c3704c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd63ee712c81908da60aa0df58efe0 |
completed | March 20, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be1078784c81908e9a3fd0b168cadc |
completed | March 21, 2026, 3:28 a.m. |
Created at: March 20, 2026, 1:17 p.m.