Triple
T1866222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Holmes (stuntman) |
E34927
|
entity |
| Predicate | co-star |
P14987
|
FINISHED |
| Object | Daniel Radcliffe |
E95151
|
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: Daniel Radcliffe | Statement: [David Holmes (stuntman), co-star, Daniel Radcliffe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daniel Radcliffe Context triple: [David Holmes (stuntman), co-star, Daniel Radcliffe]
-
A.
Daniel Radcliffe
chosen
Daniel Radcliffe is an English actor best known for playing the title role in the Harry Potter film series.
-
B.
Rupert Grint
Rupert Grint is an English actor best known for playing Ron Weasley in the Harry Potter film series.
-
C.
Rupert Friend
Rupert Friend is an English actor known for roles in films like "Pride & Prejudice" and the TV series "Homeland."
-
D.
Fionn Whitehead
Fionn Whitehead is a British actor best known for his breakout leading role in Christopher Nolan’s World War II film "Dunkirk."
-
E.
Nicholas Hoult
Nicholas Hoult is an English actor known for his versatile roles in films such as "About a Boy," the "X-Men" series, and "Mad Max: Fury Road," as well as the TV series "Skins" and "The Great."
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb0b5978c81909390f2cbd716ccaf |
completed | March 7, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69add1d540c0819099558507bdf2ffa4 |
completed | March 8, 2026, 7:45 p.m. |
Created at: March 4, 2026, 7:34 p.m.