Triple

T5126060
Position Surface form Disambiguated ID Type / Status
Subject Mars Reconnaissance Orbiter E115585 entity
Predicate alternateName P39 FINISHED
Object MRO E495765 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: MRO | Statement: [Mars Reconnaissance Orbiter, alternateName, MRO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MRO
Context triple: [Mars Reconnaissance Orbiter, alternateName, MRO]
  • A. MRO chosen
    MRO is a NASA spacecraft orbiting Mars that conducts high-resolution imaging and scientific observations of the planet’s surface, atmosphere, and subsurface.
  • B. 9M-MRO
    9M-MRO was the Boeing 777-200ER airliner operated by Malaysia Airlines that disappeared in 2014 while flying as Flight MH370.
  • C. EMRO
    EMRO is the World Health Organization’s regional office responsible for public health coordination and support across the Eastern Mediterranean region.
  • D. M&R
    M&R is the commonly used abbreviation for Murray & Roberts, a South African engineering and construction services company.
  • E. MTS
    MTS is a public transportation agency that operates bus and rail services in the San Diego metropolitan area of California.
  • 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd78228b2081908c70efd3db71f8d4 completed March 20, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69becfd49f648190a81940e7abf7d62a completed March 21, 2026, 5:05 p.m.
Created at: March 20, 2026, 1:42 p.m.