Triple

T188901
Position Surface form Disambiguated ID Type / Status
Subject Latin Extended-B E3673 entity
Predicate isAdjacentTo P5707 FINISHED
Object Latin Extended-A E3673 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: Latin Extended-A | Statement: [Latin Extended-B, isAdjacentTo, Latin Extended-A]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latin Extended-A
Context triple: [Latin Extended-B, isAdjacentTo, Latin Extended-A]
  • A. Latin Extended-B chosen
    Latin Extended-B is a Unicode block that adds additional Latin characters used for various historical, phonetic, and minority language orthographies beyond the basic Latin set.
  • B. Latin-1 Supplement
    Latin-1 Supplement is a Unicode block that extends the basic Latin script with additional characters, including accented letters and symbols used in many Western European languages.
  • C. Cyrillic Extended-B
    Cyrillic Extended-B is a Unicode block that contains additional Cyrillic characters used for writing various minority and historic languages that employ the Cyrillic script.
  • D. Latin alphabet
    The Latin alphabet is the writing system originally used for Latin that has become the most widely adopted script in the world, forming the basis of many modern languages including English, Spanish, and French.
  • E. Oscan alphabet
    The Oscan alphabet is an ancient writing system used by the Oscan-speaking peoples of pre-Roman Italy to record their language, derived from and closely related to other Old Italic scripts.
  • 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: isAdjacentTo
Context triple: [Latin Extended-B, isAdjacentTo, Latin Extended-A]
  • A. adjacentToInfrastructure
    Indicates that one entity is located directly next to or in immediate proximity to a piece of infrastructure.
  • B. adjacentIslandArc
    Indicates that one island arc is directly next to or bordering another island arc in geographic space.
  • C. hasJunctionWith
    Indicates that one entity meets or intersects with another at a shared junction point.
  • D. locatedBetween
    Indicates that one entity is positioned spatially between two other reference entities.
  • E. connectsTo
    Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
  • 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_69a2548debd48190ae3a06d6e65b53c6 completed Feb. 28, 2026, 2:35 a.m.
NER Named-entity recognition batch_69a2594abeec8190a48f36817e647fcd completed Feb. 28, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69a305e511a08190a560125ed3839a0c completed Feb. 28, 2026, 3:12 p.m.
PD Predicate disambiguation batch_69a25672332081909386f35f3ca15dd2 completed Feb. 28, 2026, 2:44 a.m.
PDg Predicate description generation batch_69a25738b5108190866fd704fceee18a completed Feb. 28, 2026, 2:47 a.m.
Created at: Feb. 28, 2026, 2:41 a.m.