Triple

T22243567
Position Surface form Disambiguated ID Type / Status
Subject Phantom Ray E549783 entity
Predicate relatedProgram P37 FINISHED
Object Boeing X-45 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: Boeing X-45 | Statement: [Phantom Ray, relatedProgram, Boeing X-45]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boeing X-45
Context triple: [Phantom Ray, relatedProgram, Boeing X-45]
  • A. Boeing X-45 chosen
    The Boeing X-45 is an experimental unmanned combat air vehicle (UCAV) developed for the U.S. military to demonstrate autonomous strike and reconnaissance capabilities.
  • B. X-47A Pegasus
    X-47A Pegasus is an experimental unmanned combat air vehicle (UCAV) developed by Northrop Grumman as an early stealthy, tailless demonstrator for carrier-capable drone technologies.
  • C. Boeing X-36
    The Boeing X-36 is an experimental unmanned tailless fighter aircraft demonstrator designed to test advanced agility and stealth technologies.
  • D. X-47B
    The X-47B is an experimental unmanned combat air vehicle (UCAV) designed to demonstrate carrier-based autonomous flight and strike capabilities for the U.S. Navy.
  • E. Lockheed Martin X-44 MANTA
    The Lockheed Martin X-44 MANTA was a conceptual experimental aircraft design exploring a tailless, thrust-vectoring configuration to improve maneuverability and stealth.
  • 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_69e11e41d9408190bd770cf282e22753 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1321655b0819091f1ddf06c67f3c2 completed April 28, 2026, 10:17 p.m.
Created at: April 16, 2026, 8:38 p.m.