Triple

T1538540
Position Surface form Disambiguated ID Type / Status
Subject Florida Supreme Court Building E32810 entity
Predicate locatedIn P40 FINISHED
Object Tallahassee E10084 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: Tallahassee | Statement: [Florida Supreme Court Building, locatedIn, Tallahassee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tallahassee
Context triple: [Florida Supreme Court Building, locatedIn, Tallahassee]
  • A. Tallahassee chosen
    Tallahassee is a city in the Florida Panhandle known for its government institutions, universities, and rolling, forested hills.
  • B. Gainesville
    Gainesville is a rapidly growing suburban community in Northern Virginia known for its residential developments, shopping centers, and proximity to Washington, D.C.
  • C. Tallahassee metropolitan area
    The Tallahassee metropolitan area is a regional urban and economic hub in northern Florida centered on the state capital and its surrounding communities.
  • D. Ocala
    Ocala is a city in north-central Florida known for its thoroughbred horse farms and historic downtown.
  • E. Sanford
    Sanford is the given first name of legendary American Major League Baseball pitcher Sandy Koufax.
  • 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_69a885ed29088190a3c2d5a3d100c16e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9082c186c81909c5c4c1a8a47c603 completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada967e01481908802baf2de7ad6a7 completed March 8, 2026, 4:52 p.m.
Created at: March 4, 2026, 7:26 p.m.