Triple

T6947366
Position Surface form Disambiguated ID Type / Status
Subject Futenma Air Station E160830 entity
Predicate ICAOCode P419 FINISHED
Object ROTM
ROTM is the ICAO airport code for Marine Corps Air Station Futenma, a United States Marine Corps airbase located in Okinawa, Japan.
 E631334 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: ROTM | Statement: [Futenma Air Station, ICAOCode, ROTM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ROTM
Context triple: [Futenma Air Station, ICAOCode, ROTM]
  • A. ROT
    ROT is the ICAO airline designator for TAROM, the flag carrier airline of Romania.
  • B. ROT
    ROT is the IATA airport code for Rotorua Airport in Rotorua, New Zealand.
  • C. ROLT
    ROLT is the acronym for the Regional Organizations Liaison Team, a group that coordinates and facilitates communication and collaboration among various regional organizations.
  • D. TRO
    TRO is the National Rail station code for Trowbridge railway station in Wiltshire, England.
  • E. RWC
    RWC (Real World Crypto) is a leading annual conference focused on practical and applied cryptography, bringing together researchers and industry practitioners to discuss real-world cryptographic systems and challenges.
  • 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: ROTM
Triple: [Futenma Air Station, ICAOCode, ROTM]
Generated description
ROTM is the ICAO airport code for Marine Corps Air Station Futenma, a United States Marine Corps airbase located in Okinawa, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ROTM
Target entity description: ROTM is the ICAO airport code for Marine Corps Air Station Futenma, a United States Marine Corps airbase located in Okinawa, Japan.
  • A. ROT
    ROT is the IATA airport code for Rotorua Airport in Rotorua, New Zealand.
  • B. ROT
    ROT is the ICAO airline designator for TAROM, the flag carrier airline of Romania.
  • C. ROLT
    ROLT is the acronym for the Regional Organizations Liaison Team, a group that coordinates and facilitates communication and collaboration among various regional organizations.
  • D. TRO
    TRO is the National Rail station code for Trowbridge railway station in Wiltshire, England.
  • E. RWC
    RWC (Real World Crypto) is a leading annual conference focused on practical and applied cryptography, bringing together researchers and industry practitioners to discuss real-world cryptographic systems and challenges.
  • 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_69c68850419081909fb426b8f5a304c7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da8beb408190b5c87a354c614cf2 completed March 27, 2026, 7:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c75870719481908312b387a3c6ce81 completed March 28, 2026, 4:26 a.m.
NEDg Description generation batch_69c759d65a008190a6121949651dcd5c completed March 28, 2026, 4:32 a.m.
NED2 Entity disambiguation (via description) batch_69c75a7a0af88190abf9d1dc4efd8b29 completed March 28, 2026, 4:35 a.m.
Created at: March 27, 2026, 2:28 p.m.