Triple

T10929925
Position Surface form Disambiguated ID Type / Status
Subject The Green Line E258174 entity
Predicate title P38 FINISHED
Object The Green Line E258174 NE FINISHED

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: The Green Line | Statement: [The Green Line, title, The Green Line]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: The Green Line
Context triple: [The Green Line, title, The Green Line]
  • A. The Green Line chosen
    The Green Line is a famous 1905 Fauvist portrait by Henri Matisse depicting his wife Amélie with a bold green stripe dividing her face, exemplifying his radical use of color and form.
  • B. Green Line
    The Green Line is one of the color-coded rapid transit routes in Atlanta’s MARTA rail system, serving key stations on the city’s east–west corridor.
  • C. Green Line
    The Green Line is a light rail and subway–surface transit line in Philadelphia operated by SEPTA, serving multiple routes that run through Center City and into West Philadelphia.
  • D. Green Line
    The Green Line is the demarcation line established in the 1949 Armistice Agreements that serves as the internationally recognized boundary between Israel and the territories captured in 1967, including the West Bank.
  • E. Green Line
    The Green Line is one of the primary rapid transit lines of Montreal's Metro system, running east–west through several of the city's busiest central and residential areas.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7709f92088190a15ae3638d3b14fb completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2175711d4819088f93bdf64ba4d3f completed April 17, 2026, 11:19 a.m.
Created at: April 8, 2026, 9:22 p.m.