Triple
T29524272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angleterre Hotel |
E749020
|
entity |
| Predicate | sharesBuildingComplexWith |
P37166
|
FINISHED |
| Object | Hotel Astoria |
—
|
NE NERFINISHED |
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: Hotel Astoria | Statement: [Angleterre Hotel, sharesBuildingComplexWith, Hotel Astoria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesBuildingComplexWith Context triple: [Angleterre Hotel, sharesBuildingComplexWith, Hotel Astoria]
-
A.
sharesBuildingWith
Indicates that two entities occupy or use the same building.
-
B.
sharesComplexWith
chosen
Indicates that two entities are components of, or co-residents within, the same larger complex or composite structure.
-
C.
belongsToBuildingComplex
Indicates that one building or structure is part of, or included within, a larger building complex.
-
D.
buildingComplex
Indicates a relationship where multiple buildings are grouped and function together as a single integrated complex.
-
E.
appliesToBuildingComplex
Indicates that something (such as a rule, condition, attribute, or action) is relevant or applicable to an entire building complex rather than to individual buildings or units.
- 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_69f0bd46d99c81908ba9d01cc1dbef7d |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69fde9fc184c8190bebef35df0e76076 |
completed | May 8, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69fde6e5beb4819094945a695e961d88 |
completed | May 8, 2026, 1:36 p.m. |
Created at: April 28, 2026, 4:44 p.m.