Triple
T14047002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Town |
E337981
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Egmore |
E336211
|
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: Egmore | Statement: [Park Town, adjacentTo, Egmore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Egmore Context triple: [Park Town, adjacentTo, Egmore]
-
A.
Egmore
chosen
Egmore is a prominent neighborhood in central Chennai, India, known as a major cultural, commercial, and transportation hub of the city.
-
B.
Tilehurst
Tilehurst is a suburban area and former village on the western edge of Reading in Berkshire, England, known for its residential character and proximity to the River Thames.
-
C.
Valsad
Valsad is a coastal city in southern Gujarat, India, known for its significant Parsi community, historical trading importance, and surrounding chikoo orchards.
-
D.
Greenhills
Greenhills is a major commercial and shopping complex in San Juan, Metro Manila, known for its vast array of retail stalls, bargain goods, and electronics.
-
E.
Greenhills
Greenhills is a suburban area in Dublin, Ireland, known for its residential character and local amenities.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de312df37081909f45ce3e219af5dc |
completed | April 14, 2026, 12:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc34332448190b044f55f0f85d5e2 |
completed | May 6, 2026, 10:40 p.m. |
Created at: April 9, 2026, 10:20 p.m.