Triple
T17306575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John "Soap" MacTavish |
E420178
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Neil Ellice |
E935485
|
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: Neil Ellice | Statement: [John "Soap" MacTavish, voiceActor, Neil Ellice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neil Ellice Context triple: [John "Soap" MacTavish, voiceActor, Neil Ellice]
-
A.
Neil Ellice
chosen
Neil Ellice is a Scottish actor best known in gaming for portraying Sergeant "Soap" MacTavish in the Call of Duty: Modern Warfare series.
-
B.
Mike Eley
Mike Eley is a British cinematographer known for his work on acclaimed films and television dramas.
-
C.
Kevin Elson
Kevin Elson is an American record producer and live sound engineer best known for his work with the rock band Journey, including on their hit "Don't Stop Believin'."
-
D.
Ben Elliot
Ben Elliot is a British Conservative Party politician and businessman who served as Co-Chairman of the Conservative Party and is known for his influential role in political fundraising.
-
E.
Elliot Cowan
Elliot Cowan is a British actor known for his work in film, television, and theatre, including roles in projects such as "Lost in Austen" and "Da Vinci's Demons."
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e438ff3ee08190ab4c44a22f86b38b |
completed | April 19, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c440c58819084792fcd6b7a7a79 |
completed | May 11, 2026, 7:59 a.m. |
Created at: April 10, 2026, 5:43 a.m.