Triple

T2110026
Position Surface form Disambiguated ID Type / Status
Subject Khalid Sheikh Mohammed E42479 entity
Predicate alsoKnownAs P39 FINISHED
Object KSM
KSM is the commonly used acronym for Khalid Sheikh Mohammed, the alleged principal architect of the September 11, 2001 terrorist attacks.
 E234622 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: KSM | Statement: [Khalid Sheikh Mohammed, alsoKnownAs, KSM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KSM
Context triple: [Khalid Sheikh Mohammed, alsoKnownAs, KSM]
  • A. KSMF
    KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital region.
  • B. KSL
    KSL is the primary sign language used by the Deaf community in South Korea, with its own distinct grammar and vocabulary separate from spoken Korean.
  • C. KS
    KS is the standard two-letter postal abbreviation for the U.S. state of Kansas.
  • D. KMSP
    KMSP is the ICAO airport code for Minneapolis–Saint Paul International Airport, a major air transportation hub serving the Minneapolis–Saint Paul metropolitan area in Minnesota, USA.
  • E. KOS
    KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
  • 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: KSM
Triple: [Khalid Sheikh Mohammed, alsoKnownAs, KSM]
Generated description
KSM is the commonly used acronym for Khalid Sheikh Mohammed, the alleged principal architect of the September 11, 2001 terrorist attacks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KSM
Target entity description: KSM is the commonly used acronym for Khalid Sheikh Mohammed, the alleged principal architect of the September 11, 2001 terrorist attacks.
  • A. KSMF
    KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital region.
  • B. KSL
    KSL is the primary sign language used by the Deaf community in South Korea, with its own distinct grammar and vocabulary separate from spoken Korean.
  • C. KS
    KS is the standard two-letter postal abbreviation for the U.S. state of Kansas.
  • D. KMSP
    KMSP is the ICAO airport code for Minneapolis–Saint Paul International Airport, a major air transportation hub serving the Minneapolis–Saint Paul metropolitan area in Minnesota, USA.
  • E. KOS
    KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
  • 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_69a8871040f08190aac2e2d0ab6b47ad completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbae1bacc8190beffc9d0470e9190 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae30721e1c8190869d577f58015141 completed March 9, 2026, 2:29 a.m.
NEDg Description generation batch_69ae3112c4648190952ad02ef8037b36 completed March 9, 2026, 2:31 a.m.
NED2 Entity disambiguation (via description) batch_69ae3199909881909ffca021098c98ea completed March 9, 2026, 2:34 a.m.
Created at: March 4, 2026, 7:43 p.m.