Triple
T12306580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EPIP Zone |
E293367
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | ITPL |
E293365
|
NE FINISHED |
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: ITPL | Statement: [EPIP Zone, near, ITPL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ITPL Context triple: [EPIP Zone, near, ITPL]
-
A.
ITPL
chosen
ITPL (International Tech Park Limited) is a major technology and business park in Whitefield, Bengaluru, housing numerous multinational IT and ITES companies.
-
B.
ITL
ITL was the former national currency of Italy before the adoption of the euro.
-
C.
ITPB
ITPB is a major technology and business park in Bangalore, India, housing numerous multinational IT and software companies.
-
D.
Ipy
Ipy was an ancient Egyptian queen consort of the 11th Dynasty, known as one of the wives of Pharaoh Mentuhotep II.
-
E.
ITP
ITP is the commonly used abbreviation for ITP Aero, a Spanish company specializing in the design, manufacture, and maintenance of aircraft engines and gas turbines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f00695c8190b7365e4593631690 |
completed | April 10, 2026, 6:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62a9d50b081908f0bdb7a2ca2832a |
completed | May 2, 2026, 4:47 p.m. |
Created at: April 8, 2026, 9:53 p.m.