Triple
T29277670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Bureau of Investigation (Philippines) |
E742285
|
entity |
| Predicate | isCivilianAgency |
P4480
|
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: [National Bureau of Investigation (Philippines), isCivilianAgency, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCivilianAgency Context triple: [National Bureau of Investigation (Philippines), isCivilianAgency, true]
-
A.
isCivilianOffice
chosen
Indicates that an office or position is non-military and belongs to the civilian sphere of authority or administration.
-
B.
isCivilian
Indicates that an entity is a non-military, non-combatant individual in the context of a given situation or system.
-
C.
isCivilMilitary
Indicates that an entity or relationship involves both civilian and military components or functions.
-
D.
isCivilianCommunityFor
Indicates that one entity functions as a civilian community associated with, serving, or surrounding another entity.
-
E.
isCivil
Indicates that one party behaves in a polite, respectful, and non-hostile manner toward another.
- 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_69f0912124d48190a046642b69407f4c |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f665130c7081908d42c2d803ed47d1 |
completed | May 2, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 12:52 p.m.