Triple
T17621816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilah Morgan |
E429724
|
entity |
| Predicate | enemyOf |
P437
|
FINISHED |
| Object | Charles Gunn |
—
|
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: Charles Gunn | Statement: [Lilah Morgan, enemyOf, Charles Gunn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Gunn Context triple: [Lilah Morgan, enemyOf, Charles Gunn]
-
A.
Charles Gunn
chosen
Charles Gunn is a street-smart vampire hunter who becomes a key ally and member of Angel Investigations in the television series "Angel."
-
B.
Charles Gunn
Charles Gunn was an American silent film actor active in the 1910s.
-
C.
Gene Reynolds
Gene Reynolds was an American actor and Emmy-winning television producer and director, best known for co-creating and producing the acclaimed TV series M*A*S*H.
-
D.
Adam Roberts
Adam Roberts is a British science fiction author and academic known for his inventive novels, critical studies of the genre, and multiple award-winning works.
-
E.
Paul Darrow
Paul Darrow was the son of famed American lawyer Clarence Darrow and a businessman who managed many of his father's financial affairs.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46db98c54819088dadec9f6bcc559 |
completed | April 19, 2026, 5:52 a.m. |
Created at: April 10, 2026, 5:52 a.m.