Triple
T17565421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nelwyn people |
E427799
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Burglekutt |
—
|
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: Burglekutt | Statement: [Nelwyn people, notableMember, Burglekutt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burglekutt Context triple: [Nelwyn people, notableMember, Burglekutt]
-
A.
Burglekutt
chosen
Burglekutt is a pompous and antagonistic village leader from the fantasy film "Willow," known for his constant belittling of the aspiring sorcerer Willow Ufgood.
-
B.
The Burglar
The Burglar is a 1957 American film noir crime drama about a jewel thief whose carefully planned heist unravels amid betrayal and pursuit.
-
C.
De Inbreker
De Inbreker is a Dutch film featuring actor Rijk de Gooyer in a prominent role.
-
D.
Heckerling
Heckerling is the surname of American film director and screenwriter Amy Heckerling, known for works like "Fast Times at Ridgemont High" and "Clueless."
-
E.
Grottenblitz
Grottenblitz is a family-friendly powered roller coaster at Heide Park in Germany, themed around caves and underground adventure.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4592ce42c8190a54a0a328c5e8ffc |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.