Triple

T5375566
Position Surface form Disambiguated ID Type / Status
Subject Pandu E108950 entity
Predicate mother P120 FINISHED
Object Ambalika E499997 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: Ambalika | Statement: [Pandu, mother, Ambalika]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambalika
Context triple: [Pandu, mother, Ambalika]
  • A. Ambalika chosen
    Ambalika is a queen from the Indian epic Mahabharata, known as one of the wives of King Vichitravirya and mother of the Pandava lineage.
  • B. Yambu
    Yambu is a coastal city in western Saudi Arabia on the Red Sea, known as an important port and industrial center.
  • C. Ambo
    Ambo is a coastal village on Tarawa Atoll in Kiribati, known for its role as a small residential and administrative community in the central Pacific.
  • D. Taroombal
    Taroombal is a clan of the Darumbal Aboriginal people, a First Nations group traditionally associated with the Rockhampton region of central Queensland, Australia.
  • E. Amvuttra
    Amvuttra is an RNA interference (RNAi) therapeutic used to treat hereditary transthyretin-mediated (hATTR) amyloidosis by reducing the production of transthyretin protein.
  • 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd86aed2a8819089d9e699f53563db completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf293f6458819091c32080782b56ed completed March 21, 2026, 11:26 p.m.
Created at: March 20, 2026, 2:03 p.m.