Triple
T11233484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roppongi Hills |
E265883
|
entity |
| Predicate | containsOfficeTenants |
P3277
|
FINISHED |
| Object | domestic companies |
—
|
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: domestic companies | Statement: [Roppongi Hills, containsOfficeTenants, domestic companies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsOfficeTenants Context triple: [Roppongi Hills, containsOfficeTenants, domestic companies]
-
A.
hasTenants
chosen
Indicates that an entity occupies or rents space from another entity as its tenant.
-
B.
majorTeamTenant
Indicates that a major sports team is the primary tenant or long-term occupant of a particular venue or facility.
-
C.
divisionOfPrimaryTenant
Indicates that one entity is a division or sub-unit that belongs to or operates under the primary tenant entity.
-
D.
tenantedBy
Indicates that a property, land, or space is occupied or leased by a specific tenant.
-
E.
supportsMultiTenancy
Indicates that the subject system or component is capable of serving and isolating multiple distinct tenants or customer environments within a single deployment.
- 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.