Triple

T3043602
Position Surface form Disambiguated ID Type / Status
Subject Unfinished Obelisk E83188 entity
Predicate carvingTechnique P14965 FINISHED
Object directly carved from bedrock 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: directly carved from bedrock | Statement: [Unfinished Obelisk, carvingTechnique, directly carved from bedrock]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: carvingTechnique
Context triple: [Unfinished Obelisk, carvingTechnique, directly carved from bedrock]
  • A. artisticTechnique chosen
    Indicates the method, style, or process used to create or execute an artistic work.
  • B. carvedBy
    Indicates that one entity has been shaped, cut, or sculpted from a material by another entity through a carving process.
  • C. carvedInto
    Indicates that one entity has been shaped, cut, or sculpted so that it takes the form or likeness of another entity.
  • D. hasBranchCarvings
    Indicates that an entity (such as a tree or wooden object) possesses carvings or engravings specifically on its branches.
  • E. hasRootCarvings
    Indicates that an object, typically a plant or tree, possesses carvings or engraved markings on its roots.
  • 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_69ad8b2298908190a7cb4e9bdbf064d0 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9b5ec5988190b8b6c95c743c6d1e completed March 8, 2026, 3:53 p.m.
PD Predicate disambiguation batch_69ad961fc62c819087c4c3a44b00847d completed March 8, 2026, 3:30 p.m.
Created at: March 8, 2026, 3:01 p.m.