Triple
T12667654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sacha Gervasi |
E302598
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sacha Gervasi |
E302598
|
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: Sacha Gervasi | Statement: [Sacha Gervasi, name, Sacha Gervasi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sacha Gervasi Context triple: [Sacha Gervasi, name, Sacha Gervasi]
-
A.
Sacha Gervasi
chosen
Sacha Gervasi is a British screenwriter and director known for films such as "The Terminal" and the documentary "Anvil! The Story of Anvil."
-
B.
Rowan Joffé
Rowan Joffé is a British screenwriter and director known for his work on films such as "28 Weeks Later" and "Brighton Rock."
-
C.
Peter Hedges
Peter Hedges is an American novelist, playwright, and filmmaker best known for writing the novel and screenplay for "What's Eating Gilbert Grape" and directing films such as "Pieces of April" and "Dan in Real Life."
-
D.
Alex Gansa
Alex Gansa is an American television writer and producer best known for co-creating and showrunning the acclaimed political thriller series "Homeland."
-
E.
Iain Softley
Iain Softley is a British film director, producer, and screenwriter known for movies such as "Backbeat," "Hackers," and "The Wings of the Dove."
- 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96181c40481908f3e2717f5472b85 |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6719de0908190bbc9a98e67e5b6eb |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:20 p.m.