Triple
T11233483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roppongi Hills |
E265883
|
entity |
| Predicate | containsResidentialUnits |
P31309
|
FINISHED |
| Object | luxury apartments |
—
|
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: luxury apartments | Statement: [Roppongi Hills, containsResidentialUnits, luxury apartments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsResidentialUnits Context triple: [Roppongi Hills, containsResidentialUnits, luxury apartments]
-
A.
isResidentialUnitOf
Indicates that a specific residential unit (e.g., apartment, house) belongs to or is part of a larger property, building, or complex.
-
B.
hasResidentialFloors
Indicates that an entity (such as a building or structure) includes one or more floors designated for residential use.
-
C.
hasHousingUnits
chosen
Indicates that an entity possesses or contains a specified number or set of housing units.
-
D.
isResidential
Indicates that something is used or designated primarily for people to live in, rather than for commercial, industrial, or other non-living purposes.
-
E.
hasResidentialArea
Indicates that an entity includes, contains, or is associated with an area designated for people to live or reside.
- 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_69d6aac656d48190b275efaa7d6074ee |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e903b8ec81909f9c89776d35c650 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfdf7a88190aae21572e57ef208 |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.