Triple
T23865939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union executive of India |
E592578
|
entity |
| Predicate | electedOfficesIncluded |
P6491
|
FINISHED |
| Object | President of India |
—
|
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: President of India | Statement: [Union executive of India, electedOfficesIncluded, President of India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electedOfficesIncluded Context triple: [Union executive of India, electedOfficesIncluded, President of India]
-
A.
electedOffice
Indicates that an entity holds or has held a particular office or position as a result of an election.
-
B.
possibleOfficeHeld
Indicates that an entity may have held, or is a candidate to have held, a particular office or position, without asserting it as a confirmed fact.
-
C.
isElectoralOffice
chosen
Indicates that the referenced position or role is an official public office filled through an electoral process.
-
D.
alsoHoldsOfficeOf
Indicates that an entity currently holding one office or position simultaneously holds another office or position as well.
-
E.
isPoliticalOffice
Indicates that the subject is a formal governmental or political position held within a public institution or authority.
- 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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cae318cc8190afd0915517964494 |
completed | April 29, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:13 p.m.