Triple

T12178845
Position Surface form Disambiguated ID Type / Status
Subject Soqotri language E290162 entity
Predicate closelyRelatedTo P37 FINISHED
Object Harsusi language E339263 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: Harsusi language | Statement: [Soqotri language, closelyRelatedTo, Harsusi language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harsusi language
Context triple: [Soqotri language, closelyRelatedTo, Harsusi language]
  • A. Harsusi language chosen
    Harsusi is a critically endangered Modern South Arabian language spoken by a small community in Oman’s Dhofar region.
  • B. Sori-Harengan language
    The Sori-Harengan language is an Oceanic language spoken in the Admiralty Islands of Papua New Guinea, belonging to the Admiralty Islands subgroup of the Austronesian language family.
  • C. Lasgerdi language
    The Lasgerdi language is an Iranian language spoken in parts of north-central Iran and classified within the Semnani branch of Northwestern Iranian languages.
  • D. Vasi-weri language
    The Vasi-weri language is a Papuan language spoken by a small indigenous community in Papua New Guinea.
  • E. Belhare language
    The Belhare language is a Kiranti language of the Sino-Tibetan family spoken by the Belhare community in eastern Nepal.
  • 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_69d6ab4d6c00819095a9a7c35de83cfb completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915fa6ff08190a1ddb3606c229cad completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a88b8748190a6c95e143f370010 completed May 2, 2026, 2:30 p.m.
Created at: April 8, 2026, 9:50 p.m.