Triple

T10731904
Position Surface form Disambiguated ID Type / Status
Subject Maltese people E253092 entity
Predicate languageSubstrate P95673 FINISHED
Object Siculo-Arabic E253089 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: Siculo-Arabic | Statement: [Maltese people, languageSubstrate, Siculo-Arabic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Siculo-Arabic
Context triple: [Maltese people, languageSubstrate, Siculo-Arabic]
  • A. Siculo-Arabic chosen
    Siculo-Arabic was a medieval variety of Arabic spoken in Sicily and parts of southern Italy that significantly influenced the development of the Maltese language.
  • B. Safaitic Arabic
    Safaitic Arabic is an ancient North Arabian dialect known from inscriptions left by nomadic tribes in the southern Syrian and northern Arabian deserts during the first centuries CE.
  • C. Ubykh
    Ubykh is an extinct Northwest Caucasian language once spoken along the eastern Black Sea coast, renowned for its exceptionally large consonant inventory and minimal vowel system.
  • D. Tamazgha
    Tamazgha is the name used by many Amazigh (Berber) people for the broader North African homeland where their communities and cultures are rooted.
  • E. Andalusian Arabic
    Andalusian Arabic was a historical variety of Arabic once spoken in Al-Andalus (the Iberian Peninsula under Muslim rule), notable for its influence on modern Spanish and North African dialects.
  • 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: languageSubstrate
Context triple: [Maltese people, languageSubstrate, Siculo-Arabic]
  • A. languageBranch
    Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
  • B. languageVariant
    Indicates that one language is a variant, dialect, or localized form of another language.
  • C. languageProvision
    Indicates that one entity supplies, supports, or makes available a particular language (or set of languages) for use by another entity.
  • D. languageForm
    Indicates the specific linguistic form or expression in which something is conveyed or represented.
  • E. languageSpecifies
    Indicates that one entity defines or constrains the syntax, semantics, or usage rules that govern how another language or linguistic system is expressed or interpreted.
  • 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_69d6aa5d8be481909a43218b2bfdbe95 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d7101f35888190b88662372a7d100d completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69dbda1d1b108190a47b46661bc85b2d completed April 12, 2026, 5:45 p.m.
PD Predicate disambiguation batch_69d6f309a44881908e49e3ba478c35b4 completed April 9, 2026, 12:30 a.m.
PDg Predicate description generation batch_69d6fa323564819097b207eb53f8a9b8 completed April 9, 2026, 1 a.m.
Created at: April 8, 2026, 9:14 p.m.