Triple

T17953265
Position Surface form Disambiguated ID Type / Status
Subject Navagraha E448883 entity
Predicate hasPart P35 FINISHED
Object Mangala 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: Mangala | Statement: [Navagraha, hasPart, Mangala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangala
Context triple: [Navagraha, hasPart, Mangala]
  • A. Mangala chosen
    Mangala is the Hindu deity associated with the planet Mars, symbolizing strength, courage, and martial energy in Vedic astrology.
  • B. Marsi
    The Marsi were an ancient Italic tribe of central Italy, known for their role in the Social War against Rome and their association with the worship of the god Mars.
  • C. Mangal
    Mangal is a given name most notably borne by Mangal Pandey, an Indian soldier whose actions helped spark the Indian Rebellion of 1857.
  • D. Mangal
    Mangal is a Pashtun tribe traditionally associated with the Karlani tribal confederation in Afghanistan and Pakistan.
  • E. Kuuk Thaayorre
    Kuuk Thaayorre is an Aboriginal Australian language spoken by the Thaayorre people of western Cape York Peninsula in Queensland, noted for its unique use of cardinal directions in everyday speech.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afae2aa081909a59a8cd4f1d04e1 completed April 19, 2026, 10:34 a.m.
Created at: April 10, 2026, 10:21 a.m.