Triple
T11431799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanded Lok Sabha constituency |
E270901
|
entity |
| Predicate | formerAssemblySegment |
P63908
|
FINISHED |
| Object | Kandhar |
—
|
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: Kandhar | Statement: [Nanded Lok Sabha constituency, formerAssemblySegment, Kandhar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerAssemblySegment Context triple: [Nanded Lok Sabha constituency, formerAssemblySegment, Kandhar]
-
A.
assemblySegments
chosen
Indicates that an entity is composed of or associated with specific component segments that together form its assembly.
-
B.
finalAssemblyBy
Indicates that one entity is responsible for performing the last stage of assembling or putting together another entity.
-
C.
hasAssembly
Indicates that an entity is composed of, or includes, one or more component parts assembled into a whole.
-
D.
traditionalAssembly
Indicates that an entity is created, constructed, or put together using conventional, established methods rather than modern or alternative techniques.
-
E.
formsInitialSegmentOf
Indicates that one entity constitutes the starting portion or beginning segment of another, larger entity or sequence.
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d806c30d788190b0c939b33de89277 |
completed | April 9, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69d7e71436f88190ac7e45a04ea5c987 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:35 p.m.