Triple
T20718465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nancy Travis |
E509241
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Duckman |
—
|
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: Duckman | Statement: [Nancy Travis, notableWork, Duckman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duckman Context triple: [Nancy Travis, notableWork, Duckman]
-
A.
Duckman
chosen
Duckman is an animated adult sitcom from the 1990s featuring a crude, wisecracking private detective duck navigating dysfunctional family life and absurd cases.
-
B.
Howard the Duck
Howard the Duck is a 1986 live-action comedy film based on the Marvel Comics character, known for its bizarre premise, cult following, and reputation as one of the most infamous box-office failures of the 1980s.
-
C.
Mr. Duck Steps Out
Mr. Duck Steps Out is a 1940 Walt Disney animated short film best known for introducing Daisy Duck as Donald Duck’s love interest.
-
D.
Watch the Duck
Watch the Duck is an American musical group known for blending electronic, R&B, and hip-hop influences with experimental production.
-
E.
Guard Duck
Guard Duck is a recurring comic character known for his overzealous, militaristic approach to security and deadpan humor.
- 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d39bec8190b3642b0d6d833375 |
completed | April 21, 2026, 12:16 a.m. |
Created at: April 16, 2026, 12:25 p.m.