Triple
T7518018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vienna House Dream Castle |
E177693
|
entity |
| Predicate | cateredFor |
P19115
|
FINISHED |
| Object | children |
—
|
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: children | Statement: [Vienna House Dream Castle, cateredFor, children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cateredFor Context triple: [Vienna House Dream Castle, cateredFor, children]
-
A.
categoryOfPeopleServed
chosen
Indicates the type or group of people that are the primary recipients or beneficiaries of a service or activity.
-
B.
intendedToServe
Indicates that one entity was designed, planned, or purposed specifically to benefit, assist, or fulfill the needs of another entity.
-
C.
cateredBy
Indicates that an event, gathering, or service is provided with food and/or drink by a particular catering entity.
-
D.
providedFor
Indicates that one entity supplies, furnishes, or makes something available to or on behalf of another entity for its use or benefit.
-
E.
servesAtThePleasureOf
Indicates that one entity holds a position or role that can be terminated at any time by another entity, typically at the discretion or will of that other 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_69c69f2891148190a484f3b8222c6f1b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5f6ccc8819080ffd123fdd59a50 |
completed | March 27, 2026, 9:26 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d44e9481909813e073b194f6f4 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:46 p.m.