Triple
T25225656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sisko's Creole Kitchen |
E632078
|
entity |
| Predicate | primaryPatronInStory |
P44585
|
FINISHED |
| Object | Benjamin Sisko |
—
|
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: Benjamin Sisko | Statement: [Sisko's Creole Kitchen, primaryPatronInStory, Benjamin Sisko]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPatronInStory Context triple: [Sisko's Creole Kitchen, primaryPatronInStory, Benjamin Sisko]
-
A.
primaryPatron
chosen
Indicates that one entity serves as the main or chief supporter, sponsor, or benefactor of another entity.
-
B.
primaryUserInStory
Indicates that a particular user is the main or central user involved in the context of a given story.
-
C.
mainPatientInStory
Indicates that an entity is the primary patient or central medical subject around which the story or narrative is focused.
-
D.
primaryActor
Indicates that the referenced entity is the main participant or most central party responsible for the action or event in the relationship.
-
E.
roleInStories
Indicates the specific function, position, or character part an entity plays within one or more stories.
- 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_69e75a8e0f688190a7aebe9a4815e25b |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f727afd5d88190ad48735cd1b32787 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72737c42c8190a3f781a5e98868ff |
completed | May 3, 2026, 10:45 a.m. |
Created at: April 21, 2026, 1:03 p.m.