Triple
T3770624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ministry of Social Affairs and Employment building |
E82787
|
entity |
| Predicate | hasTypeOfOccupant |
P21135
|
FINISHED |
| Object | civil servants |
—
|
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: civil servants | Statement: [Ministry of Social Affairs and Employment building, hasTypeOfOccupant, civil servants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfOccupant Context triple: [Ministry of Social Affairs and Employment building, hasTypeOfOccupant, civil servants]
-
A.
hasPrimaryOccupants
chosen
Indicates that certain entities are the main or principal occupants of another entity (such as a space, structure, or location).
-
B.
fieldOfOccupant
Indicates the specific professional or academic field in which an occupant is engaged or associated.
-
C.
jurisdictionOfOccupant
Indicates the legal authority or control that an occupant exercises over a place, property, or domain.
-
D.
politicalStatusOfOccupant
Indicates the political role, affiliation, or status held by the occupant of a given position, place, or office.
-
E.
hasHouseholdType
Indicates the type or category of household associated with an entity (e.g., family, single-person, shared, etc.).
- 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_69ad8b207b0081909d2b48843fbd8795 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc307cf8819090730b5e697bb197 |
completed | March 8, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69adc04ec36c8190bd5b944d4f4d32aa |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:36 p.m.