Triple
T22356479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Force Academy |
E552664
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Dundigal |
—
|
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: Dundigal | Statement: [Air Force Academy, locatedIn, Dundigal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dundigal Context triple: [Air Force Academy, locatedIn, Dundigal]
-
A.
Dundigal
chosen
Dundigal is a suburban area near Hyderabad in Telangana, India, known primarily for hosting the Indian Air Force Academy.
-
B.
Ravulapalem
Ravulapalem is a town in the Indian state of Andhra Pradesh, known for its agricultural markets and location along key transport routes in the Godavari region.
-
C.
Kondapur
Kondapur is a rapidly developing residential and commercial suburb in Hyderabad, India, known for its proximity to major IT hubs and tech parks.
-
D.
Kukatpally
Kukatpally is a major residential and commercial suburb in Hyderabad, India, known for its dense population, shopping areas, and proximity to the IT corridor.
-
E.
Tadipatri
Tadipatri is a town in the Anantapur district of Andhra Pradesh, India, known for its granite industries and historic temples.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157d08b148190a9a4e445e8579219 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:44 p.m.