Triple

T5283490
Position Surface form Disambiguated ID Type / Status
Subject Sasak E119554 entity
Predicate ISO639-3 P208 FINISHED
Object sas
sas is the ISO 639-3 code for the Sasak language spoken primarily on the Indonesian island of Lombok.
 E508397 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: sas | Statement: [Sasak, ISO639-3, sas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: sas
Context triple: [Sasak, ISO639-3, sas]
  • A. SAS
    SAS is a widely used statistical software suite for advanced analytics, business intelligence, data management, and predictive modeling.
  • B. SAS
    SAS is the School of Arts and Sciences at the University of Pennsylvania, encompassing the university’s core liberal arts and sciences departments and programs.
  • C. SAS
    SAS is an elite special forces unit of the British Army renowned for its covert operations, counterterrorism expertise, and rigorous selection process.
  • D. SAS
    SAS is a major Scandinavian airline group that provides passenger and cargo air transport services primarily across Europe and to intercontinental destinations.
  • E. SAS
    SAS is a high-speed, point-to-point serial interface standard commonly used to connect enterprise storage devices like hard drives and solid-state drives to servers.
  • 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: sas
Triple: [Sasak, ISO639-3, sas]
Generated description
sas is the ISO 639-3 code for the Sasak language spoken primarily on the Indonesian island of Lombok.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: sas
Target entity description: sas is the ISO 639-3 code for the Sasak language spoken primarily on the Indonesian island of Lombok.
  • A. SAS
    SAS is a widely used statistical software suite for advanced analytics, business intelligence, data management, and predictive modeling.
  • B. SAS
    SAS is the School of Arts and Sciences at the University of Pennsylvania, encompassing the university’s core liberal arts and sciences departments and programs.
  • C. SAS
    SAS is a high-speed, point-to-point serial interface standard commonly used to connect enterprise storage devices like hard drives and solid-state drives to servers.
  • D. SAS
    SAS is the standard abbreviation used for the NBA team San Antonio Spurs.
  • E. SAS
    SAS is a major Scandinavian airline group that provides passenger and cargo air transport services primarily across Europe and to intercontinental destinations.
  • 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_69bd446d05a8819092ad333a3f9c8d5c completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd84c8d2bc8190840699e5a526b756 completed March 20, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf06e6200881908da623e8548ec051 completed March 21, 2026, 9 p.m.
NEDg Description generation batch_69bf09d1b9088190a7bf560c8d22d225 completed March 21, 2026, 9:12 p.m.
NED2 Entity disambiguation (via description) batch_69bf0a77e3b88190904c5ed6ee48ee71 completed March 21, 2026, 9:15 p.m.
Created at: March 20, 2026, 1:52 p.m.