Triple
T132690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNICEF |
E2685
|
entity |
| Predicate | hasRepresentativeOfficesIn |
P4564
|
FINISHED |
| Object | over 190 countries and territories |
—
|
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: over 190 countries and territories | Statement: [UNICEF, hasRepresentativeOfficesIn, over 190 countries and territories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRepresentativeOfficesIn Context triple: [UNICEF, hasRepresentativeOfficesIn, over 190 countries and territories]
-
A.
establishedOffice
Indicates that an entity created or set up an official office or place of operation.
-
B.
hasHeadquartersType
Indicates the specific kind or classification of headquarters associated with an entity.
-
C.
hasHeadquartersBuilding
Indicates that an organization possesses a specific building that serves as its headquarters location.
-
D.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
E.
numberOfCountryOffices
chosen
Indicates the total count of offices or branches that an organization maintains across different countries.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a25855baf48190a1b63f2e5865d957 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2564edb488190974dc00eb9ac37d9 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.