Triple
T32678811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 303rd Special Operations Unit |
E835509
|
entity |
| Predicate | typeOfMissions |
P22637
|
FINISHED |
| Object | unconventional |
—
|
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: unconventional | Statement: [303rd Special Operations Unit, typeOfMissions, unconventional]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfMissions Context triple: [303rd Special Operations Unit, typeOfMissions, unconventional]
-
A.
typeOfMission
chosen
Indicates the specific category or nature of a mission that an entity is associated with or engaged in.
-
B.
partOfMissionType
Indicates that one entity represents a specific mission type of which the other entity is a constituent or component part.
-
C.
typeOfMissionSupport
Indicates the kind or category of support provided in relation to a specific mission.
-
D.
overseesMissionType
Indicates that one entity has responsibility for supervising or managing a particular type or category of mission carried out by another entity.
-
E.
primaryMissions
Indicates the main missions or core objectives assigned to or undertaken by an entity.
- 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_69f3493134b48190aa3c8cb523bd3800 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a007338002081908cb6340d65ff86d5 |
completed | May 10, 2026, 11:59 a.m. |
| PD | Predicate disambiguation | batch_6a0072a137ac8190a7debeb28e738e03 |
completed | May 10, 2026, 11:57 a.m. |
Created at: May 1, 2026, 1:09 a.m.