Triple
T18461452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pippa Harris |
E451045
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Sam Mendes |
—
|
NE NERFINISHED |
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: Sam Mendes | Statement: [Pippa Harris, collaboratedWith, Sam Mendes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Mendes Context triple: [Pippa Harris, collaboratedWith, Sam Mendes]
-
A.
Sam Mendes
chosen
Sam Mendes is an acclaimed British film and theatre director known for works such as "American Beauty," the James Bond films "Skyfall" and "Spectre," and the World War I epic "1917."
-
B.
Joe Wright
Joe Wright is a British film director best known for acclaimed period dramas such as "Pride & Prejudice" and "Atonement."
-
C.
Stephen Daldry
Stephen Daldry is an acclaimed British theatre and film director and producer known for works such as "Billy Elliot," "The Hours," and "The Reader."
-
D.
Simon Gavron
Simon Gavron is the father of British-American actor Rafi Gavron.
-
E.
Danny Boyle
Danny Boyle is an acclaimed British film director and producer known for movies such as "Trainspotting," "Slumdog Millionaire," and "28 Days Later."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d38345688190b565eac2e4cd7935 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e52a7fd9e081909bdf5c4aec2ba08d |
completed | April 19, 2026, 7:18 p.m. |
Created at: April 10, 2026, 11:33 a.m.