Triple
T6645572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berkeley Mansions |
E150690
|
entity |
| Predicate | hasFictionalAddressType |
P14481
|
FINISHED |
| Object | apartment building |
—
|
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: apartment building | Statement: [Berkeley Mansions, hasFictionalAddressType, apartment building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalAddressType Context triple: [Berkeley Mansions, hasFictionalAddressType, apartment building]
-
A.
hasAddress
Indicates that an entity is associated with a specific address or location.
-
B.
fictionalAddress
chosen
Indicates that an address associated with an entity is invented or not corresponding to a real-world location.
-
C.
hasFictionalProprietor
Indicates that something is owned, managed, or run by a fictional character or entity within a narrative context.
-
D.
hasFictionalProperty
Indicates that an entity possesses a property, attribute, or characteristic that exists only in a fictional or imaginary context.
-
E.
isStyleOfAddress
Indicates that one term or expression functions as a particular way of addressing or referring to another 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_69c687f1a3048190828b7342f7125d5c |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6ad04d66c8190926ffcbff372643b |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2 p.m.