Triple
T23353121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Water Study |
E592969
|
entity |
| Predicate | typicalCastType |
P27858
|
FINISHED |
| Object | ensemble dancers |
—
|
LITERAL FINISHED |
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: ensemble dancers | Statement: [Water Study, typicalCastType, ensemble dancers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalCastType Context triple: [Water Study, typicalCastType, ensemble dancers]
-
A.
typicalCast
chosen
Indicates that the associated entities form the usual or characteristic cast of characters commonly appearing in a given work or type of work.
-
B.
typicalCasting
Indicates that one entity is the usual or standard casting choice for portraying another entity (such as a role, character, or type).
-
C.
castingType
Indicates the specific method or category of casting used to transform or represent one entity in terms of another.
-
D.
castType
Indicates the specific kind or category of casting relationship that exists between two entities.
-
E.
oftenCastAs
Indicates that one entity is frequently assigned or chosen to play a particular role, type, or character in performances or representations.
- 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19a15d0a48190862179254c09c6d1 |
completed | April 29, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69effcfd8d288190937a887fe6023c11 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:20 p.m.