Triple
T26151957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palmyra Massacre |
E659850
|
entity |
| Predicate | victimAllegiance |
P121275
|
FINISHED |
| Object | Southern sympathizers |
—
|
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: Southern sympathizers | Statement: [Palmyra Massacre, victimAllegiance, Southern sympathizers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victimAllegiance Context triple: [Palmyra Massacre, victimAllegiance, Southern sympathizers]
-
A.
victimSide
chosen
Indicates that one entity is on, represents, or corresponds to the side of the victim in a conflict, incident, or harmful event.
-
B.
victimParty
Indicates that one party is the victim or harmed side in an event, action, or situation involving another party.
-
C.
victimRole
Indicates that one entity participates in an event or situation specifically in the role of the victim or harmed party.
-
D.
victimAlias
Indicates that an entity is known or referred to by an alternative name specifically in the role of a victim.
-
E.
victimCharacter
Indicates that one entity is the victim or target of harm, wrongdoing, or an adverse action carried out 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_69ee5bc5a9908190899d39ce95c6d215 |
completed | April 26, 2026, 6:39 p.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 26, 2026, 8:25 p.m.