Triple
T18821437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beowulf (2007 film) |
E460272
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Neil Gaiman |
—
|
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: Neil Gaiman | Statement: [Beowulf (2007 film), screenwriter, Neil Gaiman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neil Gaiman Context triple: [Beowulf (2007 film), screenwriter, Neil Gaiman]
-
A.
Neil Gaiman
chosen
Neil Gaiman is a British author renowned for his imaginative fantasy works across novels, comics, and screen, including "American Gods," "Coraline," and the graphic novel series "The Sandman."
-
B.
Anthony Gaiman
Anthony Gaiman is the son of American musician and performance artist Amanda Palmer and British author Neil Gaiman.
-
C.
Michael Gaiman
Michael Gaiman is one of the children of acclaimed British author Neil Gaiman.
-
D.
Gaiman
Gaiman is a small town in Argentina’s Chubut Province, known for its strong Welsh heritage, traditional tea houses, and distinctive Patagonian landscape.
-
E.
Holly Gaiman
Holly Gaiman is the daughter of acclaimed British author Neil Gaiman.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6ba90988190a93e1c2fa23b3d1d |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 10, 2026, 11:55 a.m.