Triple

T23035751
Position Surface form Disambiguated ID Type / Status
Subject MRT Line 6 E573588 entity
Predicate serves P98 FINISHED
Object Uttara 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: Uttara | Statement: [MRT Line 6, serves, Uttara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uttara
Context triple: [MRT Line 6, serves, Uttara]
  • A. Uttara
    Uttara is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • B. Uttara
    Uttara is a prince of the Matsya kingdom in the Mahabharata, known for serving as Arjuna’s charioteer during the battle against the Kaurava forces in the Virata Parva.
  • C. Uttara
    Uttara is an acclaimed Indian Bengali film directed by Buddhadeb Dasgupta, noted for its allegorical exploration of violence, faith, and rural life.
  • D. Uttara chosen
    Uttara is a major residential and commercial suburb in the northern part of Dhaka, Bangladesh, known for its planned sectors and proximity to the airport.
  • E. Uttaraa
    Uttaraa is a character from the Indian epic Mahabharata, known as the daughter of King Virata and the wife of Abhimanyu, making her the mother of Parikshit.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1850df7fc81909ee522d99d96af0d completed April 29, 2026, 4:11 a.m.
Created at: April 17, 2026, 3:53 p.m.