Triple

T7190613
Position Surface form Disambiguated ID Type / Status
Subject Florida Institute of Technology E167680 entity
Predicate hasAcronym P43 FINISHED
Object FIT
FIT is a private research university in Melbourne, Florida, known for its strong programs in engineering, science, and aeronautics.
 E647075 NE FINISHED

How this triple was built (4 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: FIT | Statement: [Florida Institute of Technology, hasAcronym, FIT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FIT
Context triple: [Florida Institute of Technology, hasAcronym, FIT]
  • A. FIT
    FIT is a software testing framework designed to facilitate collaboration between developers and customers by expressing and automatically checking requirements in tabular form.
  • B. FIT
    FIT is the National Rail station code for Filton Abbey Wood railway station in Bristol, England.
  • C. The Fit
    The Fit is a literary work by British novelist and critic Philip Hensher, known for his sharp social observation and nuanced character portrayal.
  • D. Fitter
    Fitter is the NATO reporting name for the Soviet-designed Sukhoi Su-17/20/22 family of variable-sweep wing fighter-bomber aircraft.
  • E. Fittja
    Fittja is a suburban district in the southern part of the Stockholm metropolitan area in Sweden, known for its diverse population and large-scale postwar housing.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: FIT
Triple: [Florida Institute of Technology, hasAcronym, FIT]
Generated description
FIT is a private research university in Melbourne, Florida, known for its strong programs in engineering, science, and aeronautics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FIT
Target entity description: FIT is a private research university in Melbourne, Florida, known for its strong programs in engineering, science, and aeronautics.
  • A. FIT
    FIT is a software testing framework designed to facilitate collaboration between developers and customers by expressing and automatically checking requirements in tabular form.
  • B. FIT
    FIT is the National Rail station code for Filton Abbey Wood railway station in Bristol, England.
  • C. The Fit
    The Fit is a literary work by British novelist and critic Philip Hensher, known for his sharp social observation and nuanced character portrayal.
  • D. Fitter
    Fitter is the NATO reporting name for the Soviet-designed Sukhoi Su-17/20/22 family of variable-sweep wing fighter-bomber aircraft.
  • E. Fittja
    Fittja is a suburban district in the southern part of the Stockholm metropolitan area in Sweden, known for its diverse population and large-scale postwar housing.
  • F. None of above. chosen

Provenance (5 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_69c6888b5248819090499a884ee3ec39 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e90087208190a65e49ae0e8a7cbf completed March 27, 2026, 8:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7b95c671c8190bf75b5807c6c320c completed March 28, 2026, 11:19 a.m.
NEDg Description generation batch_69c7b9d4d9e081908abc7841371c291b completed March 28, 2026, 11:21 a.m.
NED2 Entity disambiguation (via description) batch_69c7ba7c7ac88190b16ba217cdc12325 completed March 28, 2026, 11:24 a.m.
Created at: March 27, 2026, 2:50 p.m.