Triple
T1199791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fallujah |
E25752
|
entity |
| Predicate | laterConflict |
P1406
|
FINISHED |
| Object | site of fighting involving Islamic State (ISIS) after 2013 |
—
|
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: site of fighting involving Islamic State (ISIS) after 2013 | Statement: [Fallujah, laterConflict, site of fighting involving Islamic State (ISIS) after 2013]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterConflict Context triple: [Fallujah, laterConflict, site of fighting involving Islamic State (ISIS) after 2013]
-
A.
subsequentConflict
Indicates that one conflict occurs after and is temporally subsequent to another conflict.
-
B.
previousConflict
Indicates that a conflict or dispute occurred between the entities at some earlier time prior to the current context.
-
C.
endedConflict
Indicates that a previously ongoing conflict between entities has been brought to an end.
-
D.
conflictIn
chosen
Indicates that one entity is involved in, associated with, or occurs within a particular conflict or dispute.
-
E.
mainConflict
Indicates the primary opposing force, problem, or struggle that drives tension and narrative progression between entities or sides.
- 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_69a49429f5ec8190a6a205eb0ae81e5e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd9d56748190a12fe4a30346f1d8 |
completed | March 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5ed2b88190aab992913957e1cf |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.