Triple
T23705966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nizam College |
E585719
|
entity |
| Predicate | previouslyInState |
P122422
|
FINISHED |
| Object | Andhra Pradesh |
—
|
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: Andhra Pradesh | Statement: [Nizam College, previouslyInState, Andhra Pradesh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previouslyInState Context triple: [Nizam College, previouslyInState, Andhra Pradesh]
-
A.
previouslyIn
chosen
Indicates that an entity was located in, part of, or associated with another entity at some earlier time, but is not necessarily so now.
-
B.
formerState
Indicates that an entity previously held the status or condition of a particular state but no longer does so.
-
C.
predecessorStateOf
Indicates that one state occurs immediately before and leads into another state in a sequence or process.
-
D.
previousStateName
Indicates the name of the state that immediately preceded the current state in a process or state transition.
-
E.
representsStateBefore
Indicates that one state or condition existed or held true prior to another specified state or event.
- 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_69e24905f77881908194d645676acd60 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b686ef50819090a85e3ed40cfba1 |
completed | April 29, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 6:53 p.m.