Triple
T29085489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Survivor: Fiji |
E734100
|
entity |
| Predicate | featuresCastaway |
P70373
|
FINISHED |
| Object | Yau-Man Chan |
—
|
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: Yau-Man Chan | Statement: [Survivor: Fiji, featuresCastaway, Yau-Man Chan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCastaway Context triple: [Survivor: Fiji, featuresCastaway, Yau-Man Chan]
-
A.
featuresCast
chosen
Indicates that a creative work includes a particular person or group as part of its cast.
-
B.
featuresPirates
Indicates that something includes or prominently involves pirates as part of its content or subject matter.
-
C.
featuresCastFrom
Indicates that a work (such as a film or show) includes a cast member who originates from a specified source or production.
-
D.
featuresCastType
Indicates that one entity includes or highlights a particular type or category of cast (e.g., actors or performers) associated with it.
-
E.
strandedWith
Indicates that one entity is stuck or left without means to leave in the company or presence of another entity.
- 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_69f05b0c0f28819086eae6e84f2ae472 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69ff136ed2a881908f713401083970d1 |
completed | May 9, 2026, 10:58 a.m. |
| PD | Predicate disambiguation | batch_69ff10f9e3448190b6cb6ea5a67713c1 |
completed | May 9, 2026, 10:48 a.m. |
Created at: April 28, 2026, 11 a.m.