Triple

T10920686
Position Surface form Disambiguated ID Type / Status
Subject Hlai languages E257936 entity
Predicate relatedTo P37 FINISHED
Object Kra languages E260274 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: Kra languages | Statement: [Hlai languages, relatedTo, Kra languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kra languages
Context triple: [Hlai languages, relatedTo, Kra languages]
  • A. Kra languages chosen
    Kra languages are a branch of the Tai–Kadai language family spoken by various ethnic groups in southern China and neighboring regions.
  • B. Kru languages
    Kru languages are a group of closely related languages spoken primarily in Liberia and Côte d'Ivoire, known for their complex tonal systems and rich consonant inventories.
  • C. Kove–Mangseng languages
    The Kove–Mangseng languages are a small subgroup of closely related Oceanic languages spoken in parts of Papua New Guinea.
  • D. Khoe languages
    Khoe languages are a branch of southern African languages spoken mainly by Khoe peoples, known for their use of click consonants and distinct grammatical structures.
  • E. Gondi–Kui languages
    The Gondi–Kui languages are a branch of the Dravidian language family spoken primarily by tribal communities in central and eastern India, including languages such as Gondi and Kui.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77082a1488190850a4409339c3e1e completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2171adbbc8190916a5463b6e5c186 completed April 17, 2026, 11:18 a.m.
Created at: April 8, 2026, 9:22 p.m.