Triple
T19670202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | massacre at Satichaura Ghat |
E472312
|
entity |
| Predicate | sideAttacking |
P39750
|
FINISHED |
| Object | rebel sepoys |
—
|
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: rebel sepoys | Statement: [massacre at Satichaura Ghat, sideAttacking, rebel sepoys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sideAttacking Context triple: [massacre at Satichaura Ghat, sideAttacking, rebel sepoys]
-
A.
attackerSide
chosen
Indicates which party or faction is responsible for carrying out an attack in a conflict or violent incident.
-
B.
attackedFrom
Indicates that one entity initiated an attack against another entity originating from a specific source location or position.
-
C.
mainAttacker
Indicates that an entity is the primary or leading aggressor responsible for initiating or carrying out an attack against another entity.
-
D.
statusAfterAttack
Indicates the resulting condition or state of an entity after an attack has occurred.
-
E.
hasAttack
Indicates that one entity performs, possesses, or is associated with an attack directed toward 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416b9cf8819096f44e3f9fbf86fa |
completed | April 20, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69e514e941008190898d978d7bde91e4 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.