Triple

T19066171
Position Surface form Disambiguated ID Type / Status
Subject National Taiwan Museum E466663 entity
Predicate shortName P43 FINISHED
Object NTM
NTM is the abbreviation for the National Taiwan Museum, a major public museum in Taipei dedicated to Taiwan’s natural history and cultural heritage.
 E1356965 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: NTM | Statement: [National Taiwan Museum, shortName, NTM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NTM
Context triple: [National Taiwan Museum, shortName, NTM]
  • A. NTM-I
    NTM-I was a NATO-led mission focused on training and developing Iraq’s security forces and defense institutions after the 2003 invasion.
  • B. NTM-A
    NTM-A was a NATO-led mission focused on training and developing Afghanistan’s national security forces, including the army and police.
  • C. NTD
    NTD is the currency code commonly used to denote the New Taiwan dollar, the official monetary unit of Taiwan.
  • D. NGTB
    NGTB is the ICAO airport code for Abemama Atoll Airport in Kiribati, serving the island of Abemama in the central Pacific.
  • E. NTF
    NTF is a high-speed wind tunnel facility operated by NASA for advanced aerodynamic testing at transonic speeds.
  • 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: NTM
Triple: [National Taiwan Museum, shortName, NTM]
Generated description
NTM is the abbreviation for the National Taiwan Museum, a major public museum in Taipei dedicated to Taiwan’s natural history and cultural heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NTM
Target entity description: NTM is the abbreviation for the National Taiwan Museum, a major public museum in Taipei dedicated to Taiwan’s natural history and cultural heritage.
  • A. NTM-I
    NTM-I was a NATO-led mission focused on training and developing Iraq’s security forces and defense institutions after the 2003 invasion.
  • B. NTM-A
    NTM-A was a NATO-led mission focused on training and developing Afghanistan’s national security forces, including the army and police.
  • C. NTD
    NTD is the currency code commonly used to denote the New Taiwan dollar, the official monetary unit of Taiwan.
  • D. NGTB
    NGTB is the ICAO airport code for Abemama Atoll Airport in Kiribati, serving the island of Abemama in the central Pacific.
  • E. NTF
    NTF is a high-speed wind tunnel facility operated by NASA for advanced aerodynamic testing at transonic speeds.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e198621481908618f65dd01746fc completed April 20, 2026, 8:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05d3586fc88190b7e48c4afb767a2a completed May 14, 2026, 1:51 p.m.
NEDg Description generation batch_6a05d430aabc8190bdf30a16700e2476 completed May 14, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a05d4e41f108190a2d7a3a60d1e3b87 completed May 14, 2026, 1:57 p.m.
Created at: April 10, 2026, 12:03 p.m.