Triple

T126440
Position Surface form Disambiguated ID Type / Status
Subject Vulgar Latin E2560 entity
Predicate reconstructedFrom P4143 FINISHED
Object Romance languages E3592 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: Romance languages | Statement: [Vulgar Latin, reconstructedFrom, Romance languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romance languages
Context triple: [Vulgar Latin, reconstructedFrom, Romance languages]
  • A. Romance languages chosen
    Romance languages are a group of closely related languages, including Spanish, French, Italian, Portuguese, and Romanian, that evolved from Vulgar Latin spoken in the Roman Empire.
  • B. Latino-Faliscan languages
    Latino-Faliscan languages are a branch of the Italic language family that includes Latin and its closely related ancient languages spoken in central Italy.
  • C. Slavic languages
    Slavic languages are a branch of the Indo-European language family spoken primarily in Eastern and Central Europe, known for features such as rich consonant clusters, aspectual verb systems, and extensive case inflection.
  • D. Germanic languages
    Germanic languages are a major branch of the Indo-European language family that includes languages such as English, German, Dutch, and the Scandinavian languages, sharing common historical origins and linguistic features.
  • E. Vulgar Latin
    Vulgar Latin was the everyday, non-standard form of Latin spoken by common people in the Roman Empire, from which the Romance languages later evolved.
  • 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: reconstructedFrom
Context triple: [Vulgar Latin, reconstructedFrom, Romance languages]
  • A. reconstructedAs chosen
    Indicates that one entity has been rebuilt, recreated, or inferred based on evidence, models, or partial information from another entity.
  • B. reconstructedAfter
    Indicates that one entity has been rebuilt, restored, or reassembled following the occurrence or existence of another entity or event.
  • C. rebuiltFor
    Indicates that one entity has been reconstructed, renovated, or modified specifically to serve the needs, purposes, or use of another entity.
  • D. rebuiltUnder
    Indicates that an entity was reconstructed or restored while being subject to the authority, control, or governance of another entity.
  • E. relocatedFrom
    Indicates that an entity has moved or been transferred away from a specified original location.
  • F. None of above.

Provenance (4 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_69a251b54ea88190b18281669f59b4c0 completed Feb. 28, 2026, 2:23 a.m.
NER Named-entity recognition batch_69a25761e9248190a7205bfc36cb5c45 completed Feb. 28, 2026, 2:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b4b90654819092780651ae9408e9 completed Feb. 28, 2026, 9:26 a.m.
PD Predicate disambiguation batch_69a2564c11208190ad25495609d94d87 completed Feb. 28, 2026, 2:43 a.m.
Created at: Feb. 28, 2026, 2:27 a.m.