Triple
T9065235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinjar |
E217227
|
entity |
| Predicate | postConflictIssues |
P17908
|
FINISHED |
| Object | destruction of infrastructure |
—
|
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: destruction of infrastructure | Statement: [Sinjar, postConflictIssues, destruction of infrastructure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: postConflictIssues Context triple: [Sinjar, postConflictIssues, destruction of infrastructure]
-
A.
postConflictStatus
chosen
Indicates the condition or circumstances of an entity after a conflict or dispute has concluded.
-
B.
postConflictContext
Indicates that the relationship or action occurs within, or is shaped by, a setting that follows the end of an armed conflict or violent confrontation.
-
C.
reportedConflict
Indicates that one party has formally reported the existence of a conflict involving another party or situation.
-
D.
previousConflict
Indicates that a conflict or dispute occurred between the entities at some earlier time prior to the current context.
-
E.
supportedConflict
Indicates that one party provided assistance, resources, or endorsement to a side involved in a conflict or dispute.
- 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc94bc91d48190acf62afa90eec079 |
completed | April 1, 2026, 3:45 a.m. |
| PD | Predicate disambiguation | batch_69cc65f881248190bfd220bb28a9fb5f |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:11 p.m.