Triple
T18252637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddy |
E437132
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Nick Moran |
—
|
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: Nick Moran | Statement: [Eddy, portrayedBy, Nick Moran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nick Moran Context triple: [Eddy, portrayedBy, Nick Moran]
-
A.
Nick Moran
chosen
Nick Moran is an English actor and filmmaker best known for his role in the crime comedy film "Lock, Stock and Two Smoking Barrels."
-
B.
Robert Moran
Robert Moran was an American shipbuilder, businessman, and former mayor of Seattle who later became known for his conservation efforts in the San Juan Islands.
-
C.
Owen Moran
Owen Moran was a prominent early 20th-century English featherweight boxer known for his toughness and for facing many of the era’s top fighters.
-
D.
John Ronane
John Ronane was a British actor known for his work in film, television, and theatre, including a role in the drama "Elizabeth R."
-
E.
Tony Moran
Tony Moran is an American actor best known for playing the unmasked Michael Myers in John Carpenter’s original 1978 horror film "Halloween."
- 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_69d8b91104e08190a8241f7d260a5162 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4fd81ea3481909d96b5399f7a32b3 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 10:33 a.m.