Triple

T17935920
Position Surface form Disambiguated ID Type / Status
Subject Ka-Bar Knives E448464 entity
Predicate hasBrand P1500 FINISHED
Object TDI
TDI is a tactical knife brand associated with Ka-Bar, known for compact, self-defense–oriented fixed-blade designs often used by law enforcement and military personnel.
 E1296745 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: TDI | Statement: [Ka-Bar Knives, hasBrand, TDI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TDI
Context triple: [Ka-Bar Knives, hasBrand, TDI]
  • A. TDI
    TDI (Test Data In) is the serial input pin used in JTAG boundary-scan to feed test instructions and data into a device’s test access port.
  • B. TD
    TD is the two-letter ISO 3166-1 alpha-2 country code assigned to Chad.
  • C. TD
    TD is the stock ticker symbol for The Toronto-Dominion Bank, one of Canada’s largest multinational banking and financial services institutions.
  • D. TD
    TD is the post-nominal abbreviation used in Ireland to denote a Teachta Dála, a member of the lower house of the Irish parliament (Dáil Éireann).
  • E. TD
    TD is a UK postcode area covering parts of the Scottish Borders and northern England, including towns such as Galashiels and Berwick-upon-Tweed.
  • 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: TDI
Triple: [Ka-Bar Knives, hasBrand, TDI]
Generated description
TDI is a tactical knife brand associated with Ka-Bar, known for compact, self-defense–oriented fixed-blade designs often used by law enforcement and military personnel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TDI
Target entity description: TDI is a tactical knife brand associated with Ka-Bar, known for compact, self-defense–oriented fixed-blade designs often used by law enforcement and military personnel.
  • A. TDI
    TDI (Test Data In) is the serial input pin used in JTAG boundary-scan to feed test instructions and data into a device’s test access port.
  • B. TD
    TD is the two-letter ISO 3166-1 alpha-2 country code assigned to Chad.
  • C. TD
    TD is the stock ticker symbol for The Toronto-Dominion Bank, one of Canada’s largest multinational banking and financial services institutions.
  • D. TD
    TD is the post-nominal abbreviation used in Ireland to denote a Teachta Dála, a member of the lower house of the Irish parliament (Dáil Éireann).
  • E. TD
    TD is a UK postcode area covering parts of the Scottish Borders and northern England, including towns such as Galashiels and Berwick-upon-Tweed.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad924f6c8190a0d676dfa20c9918 completed April 19, 2026, 10:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03213b71188190a74c401cdc371874 completed May 12, 2026, 12:46 p.m.
NEDg Description generation batch_6a032261fd1081909ba0b04db93d16da completed May 12, 2026, 12:51 p.m.
NED2 Entity disambiguation (via description) batch_6a03232d682c8190bb9b8773609c83c2 completed May 12, 2026, 12:55 p.m.
Created at: April 10, 2026, 10:21 a.m.