Triple

T14035987
Position Surface form Disambiguated ID Type / Status
Subject Caryatids of the Erechtheion E337710 entity
Predicate functionInBuilding P112573 FINISHED
Object supporting the porch roof 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: supporting the porch roof | Statement: [Caryatids of the Erechtheion, functionInBuilding, supporting the porch roof]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: functionInBuilding
Context triple: [Caryatids of the Erechtheion, functionInBuilding, supporting the porch roof]
  • A. hasBuildingFunction
    Indicates that a building is used for or serves a particular function or purpose.
  • B. seatBuildingFunction
    Indicates that a building or structure serves a seating-related function, such as providing places for people to sit or be accommodated.
  • C. functionInWork
    Indicates that a particular function, role, or operation is performed, utilized, or occurs within the context of a specific work or creation.
  • D. mainBuildingCurrentFunction
    Indicates the current primary use or role that the main building serves.
  • E. towerFunction
    Indicates that one entity serves as a tower-like structure or performs the function of a tower in relation to another entity.
  • F. None of above. chosen

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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de30e312148190a6be0a3258364e6e completed April 14, 2026, 12:19 p.m.
PD Predicate disambiguation batch_69de05ab36b48190920efb1869bdb1fe completed April 14, 2026, 9:15 a.m.
PDg Predicate description generation batch_69de2398856c81908bed6070e4ca6ab1 completed April 14, 2026, 11:23 a.m.
Created at: April 9, 2026, 10:20 p.m.