Triple

T5446476
Position Surface form Disambiguated ID Type / Status
Subject Edom E122259 entity
Predicate scriptAttested P46409 FINISHED
Object Edomite script E30231 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: Edomite script | Statement: [Edom, scriptAttested, Edomite script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edomite script
Context triple: [Edom, scriptAttested, Edomite script]
  • A. Samaritan script
    The Samaritan script is an ancient consonantal writing system used by the Samaritan community to write their version of Hebrew and Aramaic, preserving a distinct tradition separate from mainstream Jewish scripts.
  • B. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • C. Ruqʿah script
    Ruqʿah script is a simple, highly legible Arabic handwriting style commonly used for everyday writing and official documents in the Arab world.
  • D. Nabataean alphabet chosen
    The Nabataean alphabet is an ancient Northwest Semitic script used by the Nabataean kingdom, which evolved from the Phoenician writing system and later gave rise to the early Arabic script.
  • E. Tigalari script
    The Tigalari script is a historical South Indian writing system used primarily to write Tulu and Sanskrit, closely related to other southern Brahmic 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: scriptAttested
Context triple: [Edom, scriptAttested, Edomite script]
  • A. scriptOfAttestation chosen
    Indicates the writing system or script in which an attestation (recorded instance) of something is written.
  • B. alsoAttestedIn
    Indicates that the same item, fact, or phenomenon is recorded or evidenced in another source, context, or location as well.
  • C. attestedBy
    Indicates that the existence, occurrence, or validity of something is supported, confirmed, or documented by a specified source or authority.
  • D. attestation
    Indicates a formal declaration or confirmation that something is true, accurate, or has been verified.
  • E. attestedAs
    Indicates that something is documented, recorded, or certified as having a particular status, form, or property.
  • 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_69bd4640f52c81909e653ec361f66d76 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd95be329c81908783420cf81b6af5 completed March 20, 2026, 6:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf413573c08190beae400c485d2132 completed March 22, 2026, 1:09 a.m.
PD Predicate disambiguation batch_69bd919e8d18819098c4af6a015e5cc2 completed March 20, 2026, 6:27 p.m.
Created at: March 20, 2026, 2:07 p.m.