Triple

T23009031
Position Surface form Disambiguated ID Type / Status
Subject Microsoft Multiplan E572856 entity
Predicate competesWith P1375 FINISHED
Object Lotus 1-2-3 NE NERFINISHED

How this triple was built (2 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: Lotus 1-2-3 | Statement: [Microsoft Multiplan, competesWith, Lotus 1-2-3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lotus 1-2-3
Context triple: [Microsoft Multiplan, competesWith, Lotus 1-2-3]
  • A. Lotus 1-2-3 chosen
    Lotus 1-2-3 is a pioneering spreadsheet software program for personal computers that became a dominant business application in the 1980s.
  • B. VisiCalc
    VisiCalc was the first widely used personal computer spreadsheet program, credited with helping to popularize the Apple II and launching the spreadsheet software category.
  • C. SuperCalc
    SuperCalc is an early spreadsheet software program popular in the 1980s, especially on CP/M and MS-DOS systems.
  • D. Microsoft Multiplan
    Microsoft Multiplan was an early spreadsheet program from Microsoft, released in the early 1980s as a competitor to VisiCalc and a precursor to Excel.
  • E. Eksel
    Eksel is a village in the Belgian municipality of Hechtel-Eksel, located in the province of Limburg.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1835919b08190ba78e182b87358d4 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.