Triple
T8561080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Disaster Management Authority |
E202691
|
entity |
| Predicate | apexBodyFor |
P46418
|
FINISHED |
| Object | disaster management in India |
—
|
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: disaster management in India | Statement: [National Disaster Management Authority, apexBodyFor, disaster management in India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: apexBodyFor Context triple: [National Disaster Management Authority, apexBodyFor, disaster management in India]
-
A.
apexOf
chosen
Indicates that one entity is the highest or most extreme point, level, or culmination of another entity or process.
-
B.
belongsToBody
Indicates that something is a part of, or under the ownership/authority of, a particular body or organization.
-
C.
appliedToBody
Indicates that something (such as a substance, treatment, or device) is put onto or used directly on a body or body part.
-
D.
definedBody
Indicates that one entity serves as the formal specification, content, or body definition of another entity.
-
E.
definesBody
Indicates that one entity specifies or determines the physical structure, form, or composition of another entity’s body.
- 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_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe94af14481908b8762e0dc61f10f |
completed | March 31, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69cbd1160fcc8190aa380a73610af731 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:20 p.m.