Triple

T11971017
Position Surface form Disambiguated ID Type / Status
Subject Smithsonian station E284918 entity
Predicate shortName P43 FINISHED
Object SMI
SMI is the station code used to designate the Smithsonian Metro station in Washington, D.C.'s rapid transit system.
 E957120 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: SMI | Statement: [Smithsonian station, shortName, SMI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SMI
Context triple: [Smithsonian station, shortName, SMI]
  • A. SMI
    SMI is the IATA airport code for Samos International Airport, the main air gateway to the Greek island of Samos.
  • B. SMI
    SMI is the Swiss Market Index, a leading stock market index that tracks the performance of major blue-chip companies listed on the SIX Swiss Exchange.
  • C. SMI
    SMI is the vehicle registration code assigned to the town of Mikołów in Poland.
  • D. SMIT
    SMIT (System Management Interface Tool) is IBM AIX’s menu-driven administrative interface used to simplify and standardize system management tasks.
  • E. SMI 20
    SMI 20 is a major Swiss stock market index comprising the 20 largest and most liquid companies listed on the SIX Swiss Exchange.
  • 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: SMI
Triple: [Smithsonian station, shortName, SMI]
Generated description
SMI is the station code used to designate the Smithsonian Metro station in Washington, D.C.'s rapid transit system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SMI
Target entity description: SMI is the station code used to designate the Smithsonian Metro station in Washington, D.C.'s rapid transit system.
  • A. SMI
    SMI is the vehicle registration code assigned to the town of Mikołów in Poland.
  • B. SMI
    SMI is the Swiss Market Index, a leading stock market index that tracks the performance of major blue-chip companies listed on the SIX Swiss Exchange.
  • C. SMI
    SMI is the IATA airport code for Samos International Airport, the main air gateway to the Greek island of Samos.
  • D. SMIT
    SMIT (System Management Interface Tool) is IBM AIX’s menu-driven administrative interface used to simplify and standardize system management tasks.
  • E. SMI 20
    SMI 20 is a major Swiss stock market index comprising the 20 largest and most liquid companies listed on the SIX Swiss Exchange.
  • 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_69d6ab2eaeb881909f7914758f859413 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9037d32e88190b1509285dc907d29 completed April 10, 2026, 2:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69f4597cf818819089b0d897c236b87b completed May 1, 2026, 7:42 a.m.
NEDg Description generation batch_69f45f89d5b08190a87312d96e61898a completed May 1, 2026, 8:08 a.m.
NED2 Entity disambiguation (via description) batch_69f464a5191881908e291943996169cb completed May 1, 2026, 8:30 a.m.
Created at: April 8, 2026, 9:46 p.m.