Triple
T14970346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arlington Road |
E373299
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Mark Pellington |
E156860
|
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: Mark Pellington | Statement: [Arlington Road, director, Mark Pellington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Pellington Context triple: [Arlington Road, director, Mark Pellington]
-
A.
Mark Pellington
chosen
Mark Pellington is an American film and music video director known for his visually striking, emotionally intense work on projects such as U2’s “One” and the film “Arlington Road.”
-
B.
Clifton Collins Jr.
Clifton Collins Jr. is an American character actor known for his versatile roles in films and television series such as "Capote," "Traffic," and "Westworld."
-
C.
David Witherspoon
David Witherspoon is a character known primarily as a member of the Witherspoon family related to Gus Witherspoon.
-
D.
James Clemons
James Clemons is an individual whose specific public notability or distinguishing background is not clearly identifiable from the given information.
-
E.
Michael Ealy
Michael Ealy is an American actor known for his roles in films like "Barbershop," "Think Like a Man," and "2 Fast 2 Furious," as well as various television series.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6e59a7c8190a1634a706ea68fda |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dc4715c81908b4745996d660f7c |
completed | May 9, 2026, 2:36 a.m. |
Created at: April 10, 2026, 2:49 a.m.