Triple

T6373012
Position Surface form Disambiguated ID Type / Status
Subject Dow Jones Transportation Average E143395 entity
Predicate abbreviation P43 FINISHED
Object DJTA
DJTA is a U.S. stock market index that tracks the performance of major transportation companies such as airlines, railroads, and trucking firms.
 E588931 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: DJTA | Statement: [Dow Jones Transportation Average, abbreviation, DJTA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DJTA
Context triple: [Dow Jones Transportation Average, abbreviation, DJTA]
  • A. DBE
    DBE is the title "Dame Commander of the Order of the British Empire," a high-ranking honor awarded in the British honours system.
  • B. WDI
    WDI is the commonly used abbreviation for the World Bank’s World Development Indicators, a comprehensive database of global development statistics.
  • C. School of Data
    School of Data is an educational initiative that helps people and organizations develop practical data literacy and data skills, particularly for civic and social impact.
  • D. jdb
    jdb is the command-line debugger for Java programs that comes bundled with the Oracle JDK.
  • E. Code for America
    Code for America is a nonprofit organization that partners with governments to improve public services through user-centered design, open-source technology, and civic tech innovation.
  • 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: DJTA
Triple: [Dow Jones Transportation Average, abbreviation, DJTA]
Generated description
DJTA is a U.S. stock market index that tracks the performance of major transportation companies such as airlines, railroads, and trucking firms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DJTA
Target entity description: DJTA is a U.S. stock market index that tracks the performance of major transportation companies such as airlines, railroads, and trucking firms.
  • A. DBE
    DBE is the title "Dame Commander of the Order of the British Empire," a high-ranking honor awarded in the British honours system.
  • B. WDI
    WDI is the commonly used abbreviation for the World Bank’s World Development Indicators, a comprehensive database of global development statistics.
  • C. School of Data
    School of Data is an educational initiative that helps people and organizations develop practical data literacy and data skills, particularly for civic and social impact.
  • D. jdb
    jdb is the command-line debugger for Java programs that comes bundled with the Oracle JDK.
  • E. Code for America
    Code for America is a nonprofit organization that partners with governments to improve public services through user-centered design, open-source technology, and civic tech innovation.
  • 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_69c008d9f4348190ab598a2913259a1c completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06829d76c819092b476631459233a completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d9203988190a535b4f06f478292 completed March 27, 2026, 7:11 a.m.
NEDg Description generation batch_69c6306eca2c81909ee4930c0dc62072 completed March 27, 2026, 7:23 a.m.
NED2 Entity disambiguation (via description) batch_69c630eb15cc8190b55c6cf60c5690d2 completed March 27, 2026, 7:25 a.m.
Created at: March 22, 2026, 4:33 p.m.