Triple
T1594408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlin State Opera |
E34246
|
entity |
| Predicate | typeOfVenue |
P10640
|
FINISHED |
| Object | opera house |
—
|
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: opera house | Statement: [Berlin State Opera, typeOfVenue, opera house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfVenue Context triple: [Berlin State Opera, typeOfVenue, opera house]
-
A.
typeOfEvent
Indicates that one entity is classified as a specific kind or category of event.
-
B.
venue
Indicates the place or location where an event, activity, or interaction takes place.
-
C.
refersToVenueType
chosen
Indicates that one entity specifies or identifies the type or category of venue associated with another entity.
-
D.
legacyVenue
Indicates that a venue has historical or long-standing significance, often preserved or recognized due to its past importance or enduring role.
-
E.
typicalVenues
Indicates that the specified locations are common or standard places where the associated activity, event, or entity usually occurs or is hosted.
- 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_69a885fdcb9c819081ce6f0b8cd477dd |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a916d413f08190a4e137e5ed262e25 |
completed | March 5, 2026, 5:38 a.m. |
| PD | Predicate disambiguation | batch_69a907bfb39c8190a31e0be14d3d52e6 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.