Triple

T13272630
Position Surface form Disambiguated ID Type / Status
Subject Mutiara SIS Al-Jufrie Airport E316102 entity
Predicate ICAOcode P419 FINISHED
Object WAML
WAML is the ICAO airport code for Mutiara SIS Al-Jufrie Airport in Palu, Central Sulawesi, Indonesia.
E1030191 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: WAML | Statement: [Mutiara SIS Al-Jufrie Airport, ICAOcode, WAML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WAML
Context triple: [Mutiara SIS Al-Jufrie Airport, ICAOcode, WAML]
  • A. WAMO
    WAMO is a Pittsburgh-area radio station historically known for its urban contemporary and hip-hop programming serving the region’s Black community.
  • B. WAMM
    WAMM is the ICAO airport code for Sam Ratulangi International Airport serving Manado in North Sulawesi, Indonesia.
  • C. WAMM
    WAMM is the abbreviation for the World Association of the Major Metropolises, an international organization that brings together and represents the interests of the world’s largest cities.
  • D. WAM
    WAM is a university art museum in Johannesburg, South Africa, known for its extensive collection of African art and its role in research and education at the University of the Witwatersrand.
  • E. WLM
    WLM (Workload Manager) is an IBM z/OS component that dynamically manages and prioritizes system workloads to meet performance goals and service-level objectives.
  • 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: WAML
Triple: [Mutiara SIS Al-Jufrie Airport, ICAOcode, WAML]
Generated description
WAML is the ICAO airport code for Mutiara SIS Al-Jufrie Airport in Palu, Central Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: WAML
Target entity description: WAML is the ICAO airport code for Mutiara SIS Al-Jufrie Airport in Palu, Central Sulawesi, Indonesia.
  • A. WAMO
    WAMO is a Pittsburgh-area radio station historically known for its urban contemporary and hip-hop programming serving the region’s Black community.
  • B. WAMM
    WAMM is the ICAO airport code for Sam Ratulangi International Airport serving Manado in North Sulawesi, Indonesia.
  • C. WAMM
    WAMM is the abbreviation for the World Association of the Major Metropolises, an international organization that brings together and represents the interests of the world’s largest cities.
  • D. WAM
    WAM is a university art museum in Johannesburg, South Africa, known for its extensive collection of African art and its role in research and education at the University of the Witwatersrand.
  • E. WLM
    WLM (Workload Manager) is an IBM z/OS component that dynamically manages and prioritizes system workloads to meet performance goals and service-level objectives.
  • 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_69d806b1d9ac8190852c5571d5bd5f0f completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99020f710819094c2618662bdc7fd completed April 11, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a51d458819080b8c8f3a4df0f52 completed May 3, 2026, 8:41 a.m.
NEDg Description generation batch_69f70b117c588190bb81ff53664cac4a completed May 3, 2026, 8:45 a.m.
NED2 Entity disambiguation (via description) batch_69f70c04da34819091e01db25741674e completed May 3, 2026, 8:49 a.m.
Created at: April 9, 2026, 9:26 p.m.