Triple

T9284507
Position Surface form Disambiguated ID Type / Status
Subject AMR Corporation E223154 entity
Predicate tickerSymbol P1447 FINISHED
Object AMR E223154 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: AMR | Statement: [AMR Corporation, tickerSymbol, AMR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AMR
Context triple: [AMR Corporation, tickerSymbol, AMR]
  • A. AMR
    AMR is the commonly used abbreviation for the Russian professional ice hockey club Amur Khabarovsk, which competes in the Kontinental Hockey League (KHL).
  • B. AMRO
    AMRO is the World Health Organization’s Regional Office responsible for public health leadership and coordination across the Americas.
  • C. Amf
    Amf is the official station code used to identify Amersfoort Centraal railway station in the Netherlands.
  • D. AMR Corporation chosen
    AMR Corporation was a major American airline holding company best known as the former parent of American Airlines and its regional affiliates.
  • E. AMRs
    AMRs (Autonomous Mobile Robots) are self-navigating robotic systems that use sensors, computing, and AI to move and operate independently in environments such as warehouses, factories, and hospitals.
  • 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_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081e72988190917f425e64631837 completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b21d8f1081909b2493151fde4a5f completed April 4, 2026, 6:39 a.m.
Created at: March 30, 2026, 7:34 p.m.