Triple

T3996006
Position Surface form Disambiguated ID Type / Status
Subject E-3 Sentry E87098 entity
Predicate hasDesignation P974 FINISHED
Object E-3
E-3 is a U.S. Air Force airborne warning and control system (AWACS) aircraft based on the Boeing 707 airframe, used for long-range surveillance, command, and control.
 E404289 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: E-3 | Statement: [E-3 Sentry, hasDesignation, E-3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: E-3
Context triple: [E-3 Sentry, hasDesignation, E-3]
  • A. E4
    E4 is a British digital television channel from Channel 4, known for airing popular entertainment, comedy, and drama series aimed primarily at younger audiences.
  • B. E1
    E1 is a central London postcode district covering parts of areas such as Whitechapel, Stepney, and Spitalfields in the East End.
  • C. E5
    E5 is the IATA airline designator assigned to Air Arabia Egypt, a low-cost carrier based in Egypt.
  • D. E-27
    E-27 is the station code assigned to one of the platforms or lines serving Tokyo’s major transit hub, Shinjuku Station.
  • E. F-3
    F-3 is a three-quarter-ton model in Ford’s first-generation postwar F-Series pickup truck lineup, known as the “Bonus-Built” trucks produced in the late 1940s and early 1950s.
  • 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: E-3
Triple: [E-3 Sentry, hasDesignation, E-3]
Generated description
E-3 is a U.S. Air Force airborne warning and control system (AWACS) aircraft based on the Boeing 707 airframe, used for long-range surveillance, command, and control.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: E-3
Target entity description: E-3 is a U.S. Air Force airborne warning and control system (AWACS) aircraft based on the Boeing 707 airframe, used for long-range surveillance, command, and control.
  • A. E4
    E4 is a British digital television channel from Channel 4, known for airing popular entertainment, comedy, and drama series aimed primarily at younger audiences.
  • B. E1
    E1 is a central London postcode district covering parts of areas such as Whitechapel, Stepney, and Spitalfields in the East End.
  • C. E5
    E5 is the IATA airline designator assigned to Air Arabia Egypt, a low-cost carrier based in Egypt.
  • D. E-27
    E-27 is the station code assigned to one of the platforms or lines serving Tokyo’s major transit hub, Shinjuku Station.
  • E. F-3
    F-3 is a three-quarter-ton model in Ford’s first-generation postwar F-Series pickup truck lineup, known as the “Bonus-Built” trucks produced in the late 1940s and early 1950s.
  • 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_69aed94118148190975e6aa4e554cde9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa2159d88190a01de8b038341916 completed March 9, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5403f14ec8190a77189c7066676f2 completed March 14, 2026, 11:02 a.m.
NEDg Description generation batch_69b54112e3788190800e295a745c4689 completed March 14, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_69b541808d548190987ad1538c647664 completed March 14, 2026, 11:07 a.m.
Created at: March 9, 2026, 3:34 p.m.