Triple

T25954283
Position Surface form Disambiguated ID Type / Status
Subject Obelisk of Theodosius E654052 entity
Predicate baseInscriptionType P16929 FINISHED
Object bilingual inscription LITERAL 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: bilingual inscription | Statement: [Obelisk of Theodosius, baseInscriptionType, bilingual inscription]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: baseInscriptionType
Context triple: [Obelisk of Theodosius, baseInscriptionType, bilingual inscription]
  • A. issuedInscription
    Indicates that an authority or source formally created and released a specific inscription or written record.
  • B. basisType
    Indicates the type or category of foundational support or underlying structure on which something is based.
  • C. inscriptionType chosen
    Indicates the specific kind or category of inscription associated with an entity (e.g., dedicatory, funerary, commemorative).
  • D. mayBeInscribedAs
    Indicates that one entity is permitted or suitable to be formally recorded, written, or engraved as another entity.
  • E. baseType
    Indicates that one entity serves as the underlying or parent type from which another entity is derived or specialized.
  • F. None of above.

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_69e7ab40ac788190a771bc499eb1ae5f completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f6049a5508819085be78ba6fbbfd69 completed May 2, 2026, 2:05 p.m.
PD Predicate disambiguation batch_69f4a10480748190a2e67bd399fc435d completed May 1, 2026, 12:48 p.m.
Created at: April 22, 2026, 8:44 a.m.