Triple
T9609019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Internal Revenue Service Building |
E232048
|
entity |
| Predicate | hasOfficeSpaceFor |
P1268
|
FINISHED |
| Object | IRS leadership |
—
|
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: IRS leadership | Statement: [Internal Revenue Service Building, hasOfficeSpaceFor, IRS leadership]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficeSpaceFor Context triple: [Internal Revenue Service Building, hasOfficeSpaceFor, IRS leadership]
-
A.
officeIsIn
Indicates that one office is located within or inside another specified place or building.
-
B.
hasOfficeType
Indicates that an entity’s office is classified as a specific type or category of office.
-
C.
associatedSpaceFacility
Indicates that there is a relationship linking an entity to a specific space-related facility with which it is connected or involved.
-
D.
hasOffice
chosen
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
E.
includedOffice
Indicates that one office is contained within, or forms part of, another office or organizational unit.
- 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_69ca8485a90c819094fe40b42fde9d70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a8300e48190bef51f61febc061d |
completed | April 1, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a6fd2481908efd131e207b8143 |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:08 p.m.