Triple
T7512317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lark Force |
E177549
|
entity |
| Predicate | assignedRole |
P16628
|
FINISHED |
| Object | garrison force |
—
|
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: garrison force | Statement: [Lark Force, assignedRole, garrison force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: assignedRole Context triple: [Lark Force, assignedRole, garrison force]
-
A.
assignsRoleTo
chosen
Indicates that one entity designates or grants a specific role or position to another entity.
-
B.
possibleRole
Indicates that an entity is capable of or eligible to serve in a particular role or function in a given context.
-
C.
ordinationRole
Indicates the specific religious or ceremonial office, function, or capacity in which an entity is formally ordained.
-
D.
roleInAppointments
Indicates the specific function or capacity an entity holds within one or more scheduled appointments.
-
E.
assignedUnder
Indicates that one entity has been given responsibility, duty, or authority to act within the scope, supervision, or framework defined by another 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_69c69f276b108190af2cc790b6554544 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5d33960819089a10c1149abf4b2 |
completed | March 27, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d44e9481909813e073b194f6f4 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:45 p.m.