Triple

T6431370
Position Surface form Disambiguated ID Type / Status
Subject School of Engineering (EPFL) E129785 entity
Predicate hasAbbreviation P43 FINISHED
Object STI
STI is the School of Engineering at EPFL, a major faculty focused on cutting-edge research and education in engineering and technology.
E591829 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: STI | Statement: [School of Engineering (EPFL), hasAbbreviation, STI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: STI
Context triple: [School of Engineering (EPFL), hasAbbreviation, STI]
  • A. STIS
    STIS is a versatile instrument on the Hubble Space Telescope that provides high-resolution imaging and spectroscopy across a wide range of wavelengths.
  • B. STRI
    STRI is the acronym for the Smithsonian Tropical Research Institute, a leading center for tropical biology and conservation research based in Panama.
  • C. ST
    ST is the commonly used abbreviation for SkyTeam, a major global airline alliance.
  • D. ST
    ST is the two-letter ISO 3166-1 alpha-2 country code representing São Tomé and Príncipe.
  • E. ST
    ST is the common abbreviation for Sound Transit, the regional public transit agency serving the Seattle metropolitan area in Washington State.
  • 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: STI
Triple: [School of Engineering (EPFL), hasAbbreviation, STI]
Generated description
STI is the School of Engineering at EPFL, a major faculty focused on cutting-edge research and education in engineering and technology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: STI
Target entity description: STI is the School of Engineering at EPFL, a major faculty focused on cutting-edge research and education in engineering and technology.
  • A. STIS
    STIS is a versatile instrument on the Hubble Space Telescope that provides high-resolution imaging and spectroscopy across a wide range of wavelengths.
  • B. STRI
    STRI is the acronym for the Smithsonian Tropical Research Institute, a leading center for tropical biology and conservation research based in Panama.
  • C. ST
    ST is the common abbreviation for Sound Transit, the regional public transit agency serving the Seattle metropolitan area in Washington State.
  • D. ST
    ST is the commonly used abbreviation for SkyTeam, a major global airline alliance.
  • E. ST
    ST is the two-letter ISO 3166-1 alpha-2 country code representing São Tomé and Príncipe.
  • 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_69c0084caac48190a7bc2ad8ba44536f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0693cadf08190aca84888a3440b3d completed March 22, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640e9ae8481909229bcf6d5e793d3 completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c641ff05c08190ab9526b095b038fa completed March 27, 2026, 8:38 a.m.
NED2 Entity disambiguation (via description) batch_69c642a344e48190bccb0f0d122fca4c completed March 27, 2026, 8:41 a.m.
Created at: March 22, 2026, 4:44 p.m.