Triple
T14588049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hosur Road |
E342368
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Electronics City |
E68085
|
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: Electronics City | Statement: [Hosur Road, connects, Electronics City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Electronics City Context triple: [Hosur Road, connects, Electronics City]
-
A.
Electronics City
chosen
Electronics City is a major technology and industrial hub in Bengaluru, India, known for housing numerous IT companies and electronics manufacturing units.
-
B.
Hardware City
Hardware City is the nickname of New Britain, Connecticut, historically known for its prominent hardware manufacturing industry.
-
C.
Micro Center
Micro Center is a U.S.-based retail chain specializing in computers, consumer electronics, and related accessories.
-
D.
Aeon Mall
Aeon Mall is a Japanese chain of large-scale shopping malls offering a wide range of retail, dining, and entertainment facilities across Asia.
-
E.
Oberoi Mall
Oberoi Mall is a prominent shopping and entertainment complex located in the Goregaon suburb of Mumbai, India.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4237d88819097f3f9a40f5be152 |
completed | April 14, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd94c1768881909eebb0dae15ac964 |
completed | May 8, 2026, 7:46 a.m. |
Created at: April 10, 2026, 1:24 a.m.