Triple
T1529073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhojpuri |
E32399
|
entity |
| Predicate | usesScriptHistorically |
P4037
|
FINISHED |
| Object | Kaithi |
—
|
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: Kaithi | Statement: [Bhojpuri, usesScriptHistorically, Kaithi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesScriptHistorically Context triple: [Bhojpuri, usesScriptHistorically, Kaithi]
-
A.
historicalScript
chosen
Indicates that an entity is or was written in, or otherwise associated with, a particular historical writing system or script.
-
B.
isHistoric
Indicates that something has significant importance or relevance in history, often due to its age, impact, or role in past events.
-
C.
hasHistoricalPrecursor
Indicates that one entity existed earlier and served as a predecessor, model, or influential forerunner to the other in a historical context.
-
D.
historicallyImplementedAs
Indicates that one entity was used or realized as another entity in the past, even if that is no longer the case.
-
E.
hasHistoricalShiftTo
Indicates a change over time in which one state, condition, or configuration is replaced or transformed into another in a historically traceable way.
- 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_69a885ea86308190998f6bc14bb91f8e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a933ddc5a881909cdf503f2bc29bd4 |
completed | March 5, 2026, 7:42 a.m. |
| PD | Predicate disambiguation | batch_69a907ae8f688190ad9000ea1e018585 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.