Triple

T4206019
Position Surface form Disambiguated ID Type / Status
Subject Susa E86185 entity
Predicate locatedIn P40 FINISHED
Object Susiana E335823 NE 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: Susiana | Statement: [Susa, locatedIn, Susiana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susiana
Context triple: [Susa, locatedIn, Susiana]
  • A. Susiana chosen
    Susiana was an ancient historical region in southwestern Iran, closely associated with the Elamite civilization and centered around the city of Susa.
  • B. Madera
    Madera is a city in California’s San Joaquin Valley known primarily as the administrative and economic center of Madera County.
  • C. Elato
    Elato is a small coral atoll and island community in Yap State of the Federated States of Micronesia, known for its traditional seafaring culture and remote Pacific setting.
  • D. Pinales
    Pinales is the botanical order of coniferous trees and shrubs that includes pines, firs, spruces, and related needle-leaved, cone-bearing plants.
  • E. Sonoyta
    Sonoyta is a small town in the Mexican state of Sonora, located near the U.S. border opposite Lukeville, Arizona, and serving as a gateway to the surrounding desert and protected natural areas.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69aed93b89f48190a31f6d57c760e42f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af03844314819092639ed7d6ef2c6e completed March 9, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b596258db88190aed602eeb2323fee completed March 14, 2026, 5:08 p.m.
Created at: March 9, 2026, 3:49 p.m.