Triple
T32647052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke Weaselton |
E834622
|
entity |
| Predicate | metaReferenceTo |
P170315
|
FINISHED |
| Object | Duke of Weselton from Frozen |
—
|
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: Duke of Weselton from Frozen | Statement: [Duke Weaselton, metaReferenceTo, Duke of Weselton from Frozen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: metaReferenceTo Context triple: [Duke Weaselton, metaReferenceTo, Duke of Weselton from Frozen]
-
A.
metaReferenceOf
chosen
Indicates that one entity serves as a meta-level reference or description of another entity, rather than being the primary object itself.
-
B.
alsoRefersTo
Indicates that one term, label, or identifier is used as an alternative designation for the same entity or concept as another.
-
C.
referenceSectionFor
Indicates a relationship where one resource serves as the reference section or reference material specifically associated with another resource.
-
D.
crossReference
Indicates that one entity refers the user to another related entity or source for additional or supporting information.
-
E.
notablyRefersTo
Indicates that one entity makes a particularly significant or noteworthy reference to another entity, beyond a routine or incidental mention.
- F. None of above.
Provenance (3 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_69f3492e773c81908afc10651e46cad3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c775d6188190b236fc4f89a11b61 |
completed | May 3, 2026, 3:56 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:07 a.m.