Triple
T36573323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BharatNet |
E902173
|
entity |
| Predicate | Phase I objective |
P79869
|
FINISHED |
| Object | connect around 100,000 gram panchayats |
—
|
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: connect around 100,000 gram panchayats | Statement: [BharatNet, Phase I objective, connect around 100,000 gram panchayats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Phase I objective Context triple: [BharatNet, Phase I objective, connect around 100,000 gram panchayats]
-
A.
phase1Purpose
chosen
Indicates that one entity serves as the specific purpose, goal, or intended outcome of the first phase of another entity, process, or project.
-
B.
firstPhaseStart
Indicates the point in time when the initial phase of a process or sequence begins.
-
C.
phase2Purpose
Indicates the specific intended goal, function, or outcome associated with the second phase of a process or project.
-
D.
phase1Section
Indicates that something belongs to, occurs within, or is associated with the first phase or section of a larger process or structure.
-
E.
earlyPhase
Indicates that the related process, project, or development is in its initial or beginning stage.
- 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.