Triple
T24882254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zimri |
E622744
|
entity |
| Predicate | reasonForMassKilling |
P93246
|
FINISHED |
| Object | to eliminate the house of Baasha |
—
|
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: to eliminate the house of Baasha | Statement: [Zimri, reasonForMassKilling, to eliminate the house of Baasha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForMassKilling Context triple: [Zimri, reasonForMassKilling, to eliminate the house of Baasha]
-
A.
reasonForAttack
chosen
Indicates that one entity’s attack on another is motivated or caused by the specified reason.
-
B.
timeOfMassViolence
Indicates the specific time at which an act or event of mass violence occurred.
-
C.
massacreOrderedBy
Indicates that a massacre was carried out under the command, authorization, or directive of a particular person or authority.
-
D.
massacreOccurred
Indicates that a large-scale, deliberate killing of multiple individuals took place in a specific event or context.
-
E.
massacrePerpetrators
Indicates that the subject is responsible for carrying out or participating in a massacre against the object.
- 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_69e2fac4aa848190b3446a3922cec150 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f606c79ad081908369605f72e65ca6 |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f602ce79ec8190b8336c2b9de18ac7 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 18, 2026, 5:24 a.m.