Triple
T7499334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glass |
E177218
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | David Dunn |
E668076
|
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: David Dunn | Statement: [Glass, featuresCharacter, David Dunn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Dunn Context triple: [Glass, featuresCharacter, David Dunn]
-
A.
David Dunn
chosen
David Dunn is the reluctant, superhumanly resilient security guard who discovers his extraordinary abilities in M. Night Shyamalan’s superhero thriller "Unbreakable."
-
B.
Tony McGill
Tony McGill is a music producer and bar owner best known as the husband of Irish actress Caitriona Balfe.
-
C.
Jack Deerson
Jack Deerson is a cinematographer best known for his work on the 1971 road movie "Two-Lane Blacktop."
-
D.
Aidan Murphy
Aidan Murphy is the Irish actor better known professionally as Aidan Gillen, recognized for roles in series like "The Wire" and "Game of Thrones."
-
E.
Jack Mullaney
Jack Mullaney was an American character actor known for his comedic roles in mid-20th-century film and television.
- 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_69c69f2696688190915a8458f2398211 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f597a0c08190b34fa283a11d98c7 |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84608021481908ce58a131d75188b |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:44 p.m.