Triple
T12882812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Eastern Hotel, Liverpool Street Station, London |
E308140
|
entity |
| Predicate | hasBallroomOrEventSpace |
P74384
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Great Eastern Hotel, Liverpool Street Station, London, hasBallroomOrEventSpace, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBallroomOrEventSpace Context triple: [Great Eastern Hotel, Liverpool Street Station, London, hasBallroomOrEventSpace, yes]
-
A.
hasBallrooms
chosen
Indicates that an entity possesses or contains one or more ballrooms as part of its facilities or structure.
-
B.
ballroomSpace
Indicates that one entity provides or constitutes a ballroom area or venue space for events or activities.
-
C.
hasConventionHalls
Indicates that an entity possesses or includes one or more convention halls as part of its facilities or infrastructure.
-
D.
hasDanceFloor
Indicates that a place or venue includes a designated area intended for dancing.
-
E.
venueOpenedForEvent
Indicates that a venue was opened or made available specifically for hosting a particular event.
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.