Triple
T3659029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Fisher King |
E77603
|
entity |
| Predicate | leadCharacter |
P1668
|
FINISHED |
| Object | Jack Lucas |
E378396
|
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: Jack Lucas | Statement: [The Fisher King, leadCharacter, Jack Lucas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jack Lucas Context triple: [The Fisher King, leadCharacter, Jack Lucas]
-
A.
Jack Lucas
chosen
Jack Lucas is a disgraced, guilt-ridden former shock jock whose search for redemption drives the central narrative of the film "The Fisher King."
-
B.
Charlie Lucas
Charlie Lucas is an actor known for his role in the film "Tea with Mussolini."
-
C.
Lance Johnson
Lance Johnson is a film producer known for his work on the biographical comedy-drama "The Life and Death of Peter Sellers."
-
D.
Marc McClure
Marc McClure is an American actor best known for playing Jimmy Olsen in the Superman film series and Dave McFly in the Back to the Future trilogy.
-
E.
Jonathan Lucas
Jonathan Lucas is a film editor known for his work on the feature film "Troop Zero."
- 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_69ad85dfc4dc8190a441864202ab2a7a |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3d48a2081908ac0f76d548a53ee |
completed | March 8, 2026, 6:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4c39796648190a83a7f1a63c653bd |
completed | March 14, 2026, 2:10 a.m. |
Created at: March 8, 2026, 3:25 p.m.