Triple

T820554
Position Surface form Disambiguated ID Type / Status
Subject Alabama E17742 entity
Predicate containsCity P294 FINISHED
Object Anniston E66579 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: Anniston | Statement: [Alabama, containsCity, Anniston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anniston
Context triple: [Alabama, containsCity, Anniston]
  • A. Anniston, Alabama chosen
    Anniston, Alabama is a small city in northeastern Alabama known historically as a planned industrial community and gateway to the nearby Appalachian foothills.
  • B. Phenix City
    Phenix City is a city in eastern Alabama located along the Chattahoochee River, directly across from Columbus, Georgia.
  • C. Prattville
    Prattville is a city in central Alabama known for its historic downtown, proximity to Montgomery, and strong ties to the manufacturing and paper industries.
  • D. Montgomery
    Montgomery is a historic market town in Powys, Wales, known for its medieval castle ruins and Georgian architecture.
  • E. Montgomery
    Montgomery is a common English and Scottish surname of Norman origin, historically associated with nobility and military figures.
  • 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_69a4937bcaac8190a322524ac6f45a5a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4ab6698d881908d8c5d91259f97ec completed March 1, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6efcc37c81908fd49ad65818eb0c completed March 7, 2026, 6:31 p.m.
Created at: March 1, 2026, 7:38 p.m.