Triple
T26731062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fosse |
E673974
|
entity |
| Predicate | featuresWorkFrom |
P51454
|
FINISHED |
| Object | Sweet Charity |
—
|
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: Sweet Charity | Statement: [Fosse, featuresWorkFrom, Sweet Charity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresWorkFrom Context triple: [Fosse, featuresWorkFrom, Sweet Charity]
-
A.
featuresWorkType
Indicates that an entity includes, supports, or is characterized by a particular type or category of work.
-
B.
workFeatured
chosen
Indicates that one work is highlighted, showcased, or given special prominence within a particular context, collection, or presentation.
-
C.
workPrimaryFeature
Indicates that the referenced work serves as the main or most prominent feature in a given context (such as a release, event, or collection).
-
D.
worksFor
Indicates that one entity is employed by or performs work on behalf of another entity, typically an organization or individual.
-
E.
worksOnFeature
Indicates that an entity is actively involved in developing, implementing, or contributing to a particular feature.
- 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_69eecda57ab481909424e98f2835e7d8 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fcda3699948190adb57625bae08091 |
completed | May 7, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fd16d08190b0aca6e19a632e99 |
completed | May 7, 2026, 6:25 p.m. |
Created at: April 27, 2026, 3:45 a.m.