Triple

T3661800
Position Surface form Disambiguated ID Type / Status
Subject Esselen language E77665 entity
Predicate possibleFamily P50224 FINISHED
Object Hokan languages E11435 NE FINISHED

How this triple was built (3 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: Hokan languages | Statement: [Esselen language, possibleFamily, Hokan languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hokan languages
Context triple: [Esselen language, possibleFamily, Hokan languages]
  • A. Hokan languages chosen
    Hokan languages are a proposed but controversial grouping of several Native American language families of the western United States and Mexico that share certain typological and lexical similarities.
  • B. Wakashan languages
    The Wakashan languages are an indigenous language family of the Pacific Northwest Coast of North America, traditionally spoken by several First Nations peoples in what is now British Columbia and northwestern Washington.
  • C. Numic languages
    The Numic languages are a branch of the Uto-Aztecan language family spoken by several Indigenous peoples of the Great Basin and surrounding regions in the western United States.
  • D. Karluk languages
    Karluk languages are a subgroup of the Turkic language family that includes major Central Asian languages such as Uzbek and Uyghur.
  • E. Siouan languages
    Siouan languages are a family of Indigenous languages of North America historically spoken by numerous Native American peoples across the Great Plains, Midwest, and Southeast.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: possibleFamily
Context triple: [Esselen language, possibleFamily, Hokan languages]
  • A. familyOf
    Indicates a familial relationship exists between the entities, such as by blood, marriage, or adoption.
  • B. possibleMother
    Indicates that one entity could be the biological or adoptive mother of another, but this relationship is uncertain or not definitively established.
  • C. containsFamily
    Indicates that one entity includes or encompasses members of a particular family group within it.
  • D. ownerFamily
    Indicates that a family has ownership or proprietary rights over a particular entity or resource.
  • E. belongsToFamily
    Indicates that an entity is a member of, or is associated as part of, a specific family group.
  • 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_69ad85dfc4dc8190a441864202ab2a7a completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc3d826d88190b0b50e8592088a36 completed March 8, 2026, 6:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b48846af9881909d71d63b8bd8d141 completed March 13, 2026, 9:57 p.m.
PD Predicate disambiguation batch_69adb847e9d881909dad2ffd0f3b6c15 completed March 8, 2026, 5:56 p.m.
PDg Predicate description generation batch_69adb97cdb788190a5ce96b21bd157ab completed March 8, 2026, 6:01 p.m.
Created at: March 8, 2026, 3:25 p.m.