Triple

T21804239
Position Surface form Disambiguated ID Type / Status
Subject SIL International E538309 entity
Predicate abbreviation P43 FINISHED
Object SIL
SIL is a global faith-based nonprofit organization specializing in linguistic research, Bible translation, and support for minority language communities.
 E1502184 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: SIL | Statement: [SIL International, abbreviation, SIL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SIL
Context triple: [SIL International, abbreviation, SIL]
  • A. SIL
    SIL (Safety Integrity Level) is a measure used in functional safety standards to quantify the required reliability and risk reduction performance of safety-related systems.
  • B. SIL
    SIL is the ICAO airline designator assigned to Silver Airways, a U.S.-based regional airline.
  • C. SILE
    SILE is a modern typesetting system and document processor designed as a more flexible, programmable successor to traditional TeX-based workflows.
  • D. SILJU
    SILJU is the UN/LOCODE designation for the city and transport hub of Ljubljana, the capital of Slovenia.
  • E. SL
    SL is a UK postcode area covering Slough and surrounding parts of Berkshire and nearby counties.
  • 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: SIL
Triple: [SIL International, abbreviation, SIL]
Generated description
SIL is a global faith-based nonprofit organization specializing in linguistic research, Bible translation, and support for minority language communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SIL
Target entity description: SIL is a global faith-based nonprofit organization specializing in linguistic research, Bible translation, and support for minority language communities.
  • A. SIL
    SIL is the ICAO airline designator assigned to Silver Airways, a U.S.-based regional airline.
  • B. SIL
    SIL (Safety Integrity Level) is a measure used in functional safety standards to quantify the required reliability and risk reduction performance of safety-related systems.
  • C. SILE
    SILE is a modern typesetting system and document processor designed as a more flexible, programmable successor to traditional TeX-based workflows.
  • D. SILJU
    SILJU is the UN/LOCODE designation for the city and transport hub of Ljubljana, the capital of Slovenia.
  • E. SL
    SL is a UK postcode area covering Slough and surrounding parts of Berkshire and nearby counties.
  • 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_69e0c4733f4081909a86622e7e6d15d2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0780126e88190a93dd8d0519eb8fc completed April 28, 2026, 9:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e84e9008190beac0f734864fc21 completed May 17, 2026, 10:17 p.m.
NEDg Description generation batch_6a0a3f4358d48190a88208a55d19a9ef completed May 17, 2026, 10:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0a404206e0819080c640619cd277ab completed May 17, 2026, 10:25 p.m.
Created at: April 16, 2026, 6:53 p.m.