Triple
T25176857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lieut-Bailiff (when acting) |
E630471
|
entity |
| Predicate | performsFunctionOf |
P49471
|
FINISHED |
| Object | Bailiff of Jersey |
—
|
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: Bailiff of Jersey | Statement: [Lieut-Bailiff (when acting), performsFunctionOf, Bailiff of Jersey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performsFunctionOf Context triple: [Lieut-Bailiff (when acting), performsFunctionOf, Bailiff of Jersey]
-
A.
performedFunction
Indicates that an entity has carried out or executed a particular function, role, or operation.
-
B.
performsFunctionAt
Indicates that an entity carries out or executes a specific function at a particular location, time, or contextual point.
-
C.
performsAs
chosen
Indicates that one entity takes on, enacts, or fulfills the role, function, or character of another entity.
-
D.
performsFrom
Indicates that an action, performance, or operation is carried out starting from a particular source, origin, or initial context.
-
E.
actualFunction
Indicates that something serves as the real, operative function or role performed in practice, as opposed to a nominal or theoretical one.
- 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_69e75a88fdf081908e47ae6e195c14e1 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f5f6baf2d48190a6a4cd6501be87d2 |
completed | May 2, 2026, 1:06 p.m. |
| PD | Predicate disambiguation | batch_69f5afd5baac8190bb8ed576813c8591 |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 12:34 p.m.