Triple

T5530946
Position Surface form Disambiguated ID Type / Status
Subject Mardi E145045 entity
Predicate title P38 FINISHED
Object Mardi E145045 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: Mardi | Statement: [Mardi, title, Mardi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mardi
Context triple: [Mardi, title, Mardi]
  • A. Mardi chosen
    "Mardi" is an 1849 novel by Herman Melville, known as his first major foray into philosophical and allegorical fiction set in a fantastical South Seas archipelago.
  • B. MARDI
    MARDI is a descent imaging camera on NASA's Curiosity rover that captured high-resolution video of the rover's landing on Mars and helps document the geology of its landing site.
  • C. Dyushambe
    Dyushambe is the former name of Dushanbe, the capital and largest city of Tajikistan.
  • D. Tandag
    Tandag is a coastal city in the Philippines that serves as the capital of the province of Surigao del Sur in the Caraga region of Mindanao.
  • E. Parjanya
    Parjanya is a figure in Hindu tradition known as the father of Nanda, the foster father of Lord Krishna.
  • 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_69c008f9955881909bfa8348b56b4739 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f9b59bc8190a8758b3be54831e9 completed March 22, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04cdccb70819081bfe0e4a56f253f completed March 22, 2026, 8:11 p.m.
Created at: March 22, 2026, 3:34 p.m.