Triple
T11320054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Polley |
E268068
|
entity |
| Predicate | actedIn |
P1668
|
FINISHED |
| Object | Mr. Nobody |
E540748
|
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: Mr. Nobody | Statement: [Sarah Polley, actedIn, Mr. Nobody]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mr. Nobody Context triple: [Sarah Polley, actedIn, Mr. Nobody]
-
A.
Mr. Nobody
Mr. Nobody is a covert government operative and ally to Dominic Toretto’s crew in the Fast & Furious film franchise.
-
B.
Mr. Nobody
chosen
Mr. Nobody is a 2009 science fiction drama film that explores alternate life paths and the nature of choice through the story of the last mortal man on Earth.
-
C.
Mr. Nobody
Mr. Nobody is a surreal, reality-warping supervillain in DC Comics known for his fragmented, abstract form and his role as a bizarre nemesis of the Doom Patrol.
-
D.
Scrappy Little Nobody
Scrappy Little Nobody is a humorous, candid collection of autobiographical essays by actress Anna Kendrick, reflecting on her unconventional path through childhood, Broadway, and Hollywood.
-
E.
Son of Rambow
Son of Rambow is a British coming-of-age comedy film about two young boys in the 1980s who set out to make their own homemade action movie inspired by First Blood.
- 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_69d6aaca5c24819083db46a30d86cb34 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9de875481908acfa56015d4b46f |
completed | April 9, 2026, 6:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e525e2549081909ec99e4c7006fd66 |
completed | April 19, 2026, 6:58 p.m. |
Created at: April 8, 2026, 9:32 p.m.