Triple
T34720961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Governor of Goa |
E1000910
|
entity |
| Predicate | officeContinuedFor |
P75675
|
FINISHED |
| Object | State of Goa |
—
|
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: State of Goa | Statement: [Governor of Goa, officeContinuedFor, State of Goa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeContinuedFor Context triple: [Governor of Goa, officeContinuedFor, State of Goa]
-
A.
officeContinuedBy
Indicates that one office or term in a position is directly succeeded or carried on by another office or term.
-
B.
officeContinuity
chosen
Indicates that the same office or official position is held continuously across a change in time, term, or context without interruption.
-
C.
officeWon
Indicates that a candidate successfully secured an elected office or position as the result of an election or selection process.
-
D.
officeIs
Indicates that one entity serves as the office or official workplace location of another entity.
-
E.
officeContingentOn
Indicates that holding or obtaining one office, position, or role is dependent on the prior existence, status, or outcome of another specified office or condition.
- 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_69f76daeb6e48190a4c9a6b0edc80f72 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ffc3f0b19c8190b5a749bc3cad21dd |
completed | May 9, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69ffc1b882808190932b2d43ea5537c9 |
completed | May 9, 2026, 11:22 p.m. |
Created at: May 3, 2026, 3:59 p.m.