Triple

T2975041
Position Surface form Disambiguated ID Type / Status
Subject Lahaina E80373 entity
Predicate languageUsed P238 FINISHED
Object Hawaiian E17029 NE FINISHED

How this triple was built (2 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: Hawaiian | Statement: [Lahaina, languageUsed, Hawaiian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hawaiian
Context triple: [Lahaina, languageUsed, Hawaiian]
  • A. Hawaiian chosen
    Hawaiian is a Polynesian language indigenous to the Hawaiian Islands, known for its unique phonology, rich oral tradition, and cultural significance to Native Hawaiians.
  • B. HAWAIIAN
    HAWAIIAN is the radio callsign used by Hawaiian Airlines, the largest and longest-operating commercial airline based in Hawaii.
  • C. Native Hawaiians
    Native Hawaiians are the Indigenous Polynesian people of the Hawaiian Islands, with a distinct language, culture, and history rooted in the Pacific.
  • D. Nukulaelae dialect
    The Nukulaelae dialect is a regional variety of the Tuvaluan (Ellicean) language spoken primarily on Nukulaelae Atoll in Tuvalu.
  • E. Marshallese language
    Marshallese is an Austronesian language spoken primarily in the Republic of the Marshall Islands, known for its complex system of consonants and vowel allophones influenced by surrounding oceanic languages.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad8b14ffe881908ffed62f9595c867 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99894bb0819099fa5cc5166c0eeb completed March 8, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b108e99ea881908cccc6656e8653c3 completed March 11, 2026, 6:17 a.m.
Created at: March 8, 2026, 2:58 p.m.