Triple
T25284901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandurbar Lok Sabha constituency |
E633911
|
entity |
| Predicate | assemblySegmentsInclude |
P121483
|
FINISHED |
| Object | Sakri Assembly constituency |
—
|
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: Sakri Assembly constituency | Statement: [Nandurbar Lok Sabha constituency, assemblySegmentsInclude, Sakri Assembly constituency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: assemblySegmentsInclude Context triple: [Nandurbar Lok Sabha constituency, assemblySegmentsInclude, Sakri Assembly constituency]
-
A.
assemblySegments
Indicates that an entity is composed of or associated with specific component segments that together form its assembly.
-
B.
hasAssemblySegment
chosen
Indicates that an object or system includes a specific segment as part of its overall assembly structure.
-
C.
assemblyLinkedTo
Indicates that one assembly is associated or connected to another assembly in a meaningful or functionally relevant way.
-
D.
assemblyRequired
Indicates that the associated item or components must be put together or constructed before they can be used.
-
E.
hasAssembly
Indicates that an entity is composed of, or includes, one or more component parts assembled into a whole.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f55e519978819087a1676564a74630 |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 1:19 p.m.