Triple
T19598075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Delhi |
E470398
|
entity |
| Predicate | hasMarket |
P2714
|
FINISHED |
| Object | Ballimaran |
—
|
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: Ballimaran | Statement: [Old Delhi, hasMarket, Ballimaran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ballimaran Context triple: [Old Delhi, hasMarket, Ballimaran]
-
A.
Ballimaran
chosen
Ballimaran is a historic, densely packed lane in Old Delhi known for its traditional shops, old havelis, and association with the poet Mirza Ghalib.
-
B.
Mahorais
Mahorais is a French-based creole language spoken primarily on the island of Mayotte in the Indian Ocean.
-
C.
Mulgimaa
Mulgimaa is a historic cultural region in southern Estonia known for its distinct Mulgi dialect, traditional folk culture, and influential role in Estonian national awakening.
-
D.
Arboria
Arboria is a lush, forested kingdom on the planet Mongo in the Flash Gordon universe, ruled by Prince Barin and known for its treetop cities and dangerous wildlife.
-
E.
Roura
Roura is a commune in French Guiana known for its rainforest landscapes and proximity to the Kaw-Roura Marshland Nature Reserve.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6407c52c081908704d3a4dd6e853b |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.