Triple
T29717316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prime Minister’s Secretariat |
E751948
|
entity |
| Predicate | usedToBeOfficialNameOf |
P62748
|
FINISHED |
| Object | Prime Minister’s Office (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: Prime Minister’s Office (India) | Statement: [Prime Minister’s Secretariat, usedToBeOfficialNameOf, Prime Minister’s Office (India)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedToBeOfficialNameOf Context triple: [Prime Minister’s Secretariat, usedToBeOfficialNameOf, Prime Minister’s Office (India)]
-
A.
formerOfficialNameOf
chosen
Indicates that one entity was previously the official name of another entity before a renaming or reclassification.
-
B.
historicalNameUsedIn
Indicates that a historical or former name was used to refer to a particular entity in some context.
-
C.
currentOfficialNameSince
Indicates the date or time from which an entity has borne its current official name.
-
D.
officialNameDuringPeriod
Indicates that an entity had a specific official name that was valid only during a particular time period.
-
E.
officialNameSince
Indicates the date or point in time from which a particular official name has been in effect for an entity.
- 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_69f0d628c00c8190ab5ee7e423d7ec3c |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 28, 2026, 7:34 p.m.