Triple
T30517410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manbij offensive |
E776602
|
entity |
| Predicate | belligerentForceComponent |
P158955
|
FINISHED |
| Object | Kurdish YPG units |
—
|
NE NERFINISHED |
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: Kurdish YPG units | Statement: [Manbij offensive, belligerentForceComponent, Kurdish YPG units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belligerentForceComponent Context triple: [Manbij offensive, belligerentForceComponent, Kurdish YPG units]
-
A.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
-
B.
forzaBelligerante
chosen
Indicates a party’s status or role as a belligerent force engaged in a conflict or war.
-
C.
enemyForceType
Indicates that one entity is characterized as a hostile or opposing force of a specified type relative to another entity.
-
D.
isPrimaryLandForceOf
Indicates that a military land force serves as the main or principal ground combat component of a specified country, alliance, or organization.
-
E.
belligerentFor
Indicates a relationship in which one entity is engaged in hostile or aggressive behavior toward, or in conflict with, 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_69f2249b23c4819087fa85496d92f43f |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68806f4888190a09e1753397c13ba |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:16 p.m.