Triple
T34239897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mothers and Sons |
E878432
|
entity |
| Predicate | hasSeatingVenueType |
P112840
|
FINISHED |
| Object | proscenium theatre |
—
|
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: proscenium theatre | Statement: [Mothers and Sons, hasSeatingVenueType, proscenium theatre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSeatingVenueType Context triple: [Mothers and Sons, hasSeatingVenueType, proscenium theatre]
-
A.
hasSeating
Indicates that one entity provides or contains seating capacity or seating arrangements for another entity.
-
B.
hasBandSeating
Indicates that a venue or location provides designated seating specifically for a band or musical ensemble.
-
C.
locatedInVenueType
chosen
Indicates that an entity is situated within or associated with a venue of a specific type (e.g., stadium, theater, restaurant).
-
D.
hasSeatingClassification
Indicates that an entity is assigned a specific type or category of seating arrangement or capacity.
-
E.
hasBoxSeating
Indicates that an entity provides or includes box seating as a type of seating arrangement.
- 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_69f349b22d8c819096b22df268382aa9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ffb5c373948190a6606e8caa87a384 |
completed | May 9, 2026, 10:31 p.m. |
| PD | Predicate disambiguation | batch_69ffb261da788190b41399df8ed895e8 |
completed | May 9, 2026, 10:17 p.m. |
Created at: May 1, 2026, 1:56 a.m.