Triple
T682510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Nations Office at Nairobi |
E13212
|
entity |
| Predicate | oneOfFourMainUNOffices |
P17491
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [United Nations Office at Nairobi, oneOfFourMainUNOffices, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oneOfFourMainUNOffices Context triple: [United Nations Office at Nairobi, oneOfFourMainUNOffices, true]
-
A.
UNRegion
Indicates that an entity belongs to, or is associated with, a specific United Nations–defined geographic region.
-
B.
UNMission
Indicates that an entity is a United Nations peacekeeping or political mission operating in a specific area or context.
-
C.
hasUNOrgan
Indicates that an entity is a member of, affiliated with, or otherwise formally associated with a specified United Nations body or organ.
-
D.
hasSpecializedAgency
Indicates that one entity possesses or is supported by an agency that is specialized in handling a particular domain, function, or set of tasks on its behalf.
-
E.
hasInternationalOrganizationOffice
Indicates that an international organization maintains an official office or physical presence at a given location.
- F. None of above. chosen
Provenance (4 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_69a4933e0f98819097d22766c49b61b8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a06f9ee88190a2d757aacd8e3f5b |
completed | March 1, 2026, 8:24 p.m. |
| PD | Predicate disambiguation | batch_69a49d1f0ccc819088c1527beabcb718 |
completed | March 1, 2026, 8:10 p.m. |
| PDg | Predicate description generation | batch_69a49df19c9481909cc9bc33ed7f011b |
completed | March 1, 2026, 8:13 p.m. |
Created at: March 1, 2026, 7:36 p.m.