Triple
T34491874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Larkin Company |
E885488
|
entity |
| Predicate | hadOfficeBuilding |
P39751
|
FINISHED |
| Object | Larkin Administration Building |
—
|
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: Larkin Administration Building | Statement: [Larkin Company, hadOfficeBuilding, Larkin Administration Building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadOfficeBuilding Context triple: [Larkin Company, hadOfficeBuilding, Larkin Administration Building]
-
A.
hasProperOffice
Indicates that an entity maintains an officially designated, appropriate office or place of business.
-
B.
hasOfficeBuildings
chosen
Indicates that one entity possesses, controls, or is associated with one or more office buildings.
-
C.
isMajorOfficeBuildingIn
Indicates that a building is a primary or significant office structure located within a specified geographic or administrative area.
-
D.
officeIsIn
Indicates that one office is located within or inside another specified place or building.
-
E.
hasOfficeType
Indicates that an entity’s office is classified as a specific type or category of office.
- 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_69f349cafcec8190997b45b3fdc16c27 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71fb1ab3881908e2f7c0e6f23db49 |
completed | May 3, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 2:01 a.m.