Triple
T38125276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maratha military leadership at Panipat |
E952049
|
entity |
| Predicate | leftWingCommander |
P139495
|
FINISHED |
| Object | Jankoji Rao Scindia |
—
|
NE NERFINISHED |
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: Jankoji Rao Scindia | Statement: [Maratha military leadership at Panipat, leftWingCommander, Jankoji Rao Scindia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftWingCommander Context triple: [Maratha military leadership at Panipat, leftWingCommander, Jankoji Rao Scindia]
-
A.
leftWingDepicts
Indicates that something shown or represented appears specifically on the left wing (or left side panel) of an object or structure.
-
B.
leftWing
chosen
Indicates that an entity is positioned on or corresponds to the left wing of another entity.
-
C.
leftWingAllianceContext
Indicates a political or ideological context in which entities are aligned with, associated with, or operating within a left-wing alliance.
-
D.
formerGuerrillaWing
Indicates that an entity previously functioned as the guerrilla (armed insurgent) wing of another organization or movement.
-
E.
militaryWingLeader
Indicates that one entity is the leader or head of the military wing or armed branch associated with 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_69f76f083548819082bd2bbf53c79e8e |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.