Triple
T18337552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliot Spencer |
E439310
|
entity |
| Predicate | loyalTo |
P1201
|
FINISHED |
| Object | Nathan Ford |
—
|
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: Nathan Ford | Statement: [Eliot Spencer, loyalTo, Nathan Ford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nathan Ford Context triple: [Eliot Spencer, loyalTo, Nathan Ford]
-
A.
Nathan Ford
chosen
Nathan Ford is the brilliant but morally conflicted former insurance investigator who leads a team of thieves and con artists in the television series "Leverage."
-
B.
Nate Ford
Nate Ford is the brilliant but morally conflicted former insurance investigator who leads the crew of con artists in the television series "Leverage."
-
C.
Nicholas Ford
Nicholas Ford is a member of the Ford family, the son of Michael Gerald Ford and a grandson of former U.S. President Gerald R. Ford.
-
D.
Nathan Harper
Nathan Harper is the teenage protagonist of the action thriller film "Abduction," who discovers his life is a lie and becomes the target of a dangerous conspiracy.
-
E.
Nathan Darrow
Nathan Darrow is an American actor best known for his roles in the television series "House of Cards" and "Gotham."
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ece387881909a5da0aa4370489c |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.