Triple

T5579527
Position Surface form Disambiguated ID Type / Status
Subject McDonnell Douglas Phantom FGR.2 E146606 entity
Predicate airForceDesignation P7137 FINISHED
Object FGR.2
FGR.2 is the Royal Air Force designation for a British variant of the McDonnell Douglas Phantom II multirole fighter aircraft.
 E531867 NE FINISHED

How this triple was built (4 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: FGR.2 | Statement: [McDonnell Douglas Phantom FGR.2, airForceDesignation, FGR.2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FGR.2
Context triple: [McDonnell Douglas Phantom FGR.2, airForceDesignation, FGR.2]
  • A. FGR4
    FGR4 is a multirole combat aircraft designation used by the Royal Air Force for the Eurofighter Typhoon in its fighter, ground-attack, and reconnaissance configuration.
  • B. GR-F
    GR-F is the ISO 3166-2 regional code assigned to the Greek administrative region of Thessaly.
  • C. FGS
    FGS is a high-precision optical instrument used on space telescopes to maintain accurate pointing and stabilization during observations.
  • D. FOGRMA
    FOGRMA is a U.S. federal law enacted in 1982 that governs the management, collection, and auditing of royalties from oil and gas production on federal and Indian lands.
  • E. FGP
    FGP is the stock ticker symbol for FirstGroup, a leading UK-based transport operator running bus and rail services in the United Kingdom and North America.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: FGR.2
Triple: [McDonnell Douglas Phantom FGR.2, airForceDesignation, FGR.2]
Generated description
FGR.2 is the Royal Air Force designation for a British variant of the McDonnell Douglas Phantom II multirole fighter aircraft.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FGR.2
Target entity description: FGR.2 is the Royal Air Force designation for a British variant of the McDonnell Douglas Phantom II multirole fighter aircraft.
  • A. FGR4
    FGR4 is a multirole combat aircraft designation used by the Royal Air Force for the Eurofighter Typhoon in its fighter, ground-attack, and reconnaissance configuration.
  • B. GR-F
    GR-F is the ISO 3166-2 regional code assigned to the Greek administrative region of Thessaly.
  • C. FGS
    FGS is a high-precision optical instrument used on space telescopes to maintain accurate pointing and stabilization during observations.
  • D. FOGRMA
    FOGRMA is a U.S. federal law enacted in 1982 that governs the management, collection, and auditing of royalties from oil and gas production on federal and Indian lands.
  • E. FGP
    FGP is the stock ticker symbol for FirstGroup, a leading UK-based transport operator running bus and rail services in the United Kingdom and North America.
  • F. None of above. chosen

Provenance (5 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_69c0090287a08190b4098411effe970c completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0206bfea08190aa2c8df9f88013ac completed March 22, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c02858a2388190a1e8c3efce8b066d completed March 22, 2026, 5:35 p.m.
NEDg Description generation batch_69c03d15e8d48190b08d0903621fbdcb completed March 22, 2026, 7:03 p.m.
NED2 Entity disambiguation (via description) batch_69c03daa883c8190a787c40965408132 completed March 22, 2026, 7:06 p.m.
Created at: March 22, 2026, 3:37 p.m.