Triple

T5087484
Position Surface form Disambiguated ID Type / Status
Subject Gandhi heritage sites in South Africa E114671 entity
Predicate hasPart P35 FINISHED
Object Phoenix Settlement E20858 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: Phoenix Settlement | Statement: [Gandhi heritage sites in South Africa, hasPart, Phoenix Settlement]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phoenix Settlement
Context triple: [Gandhi heritage sites in South Africa, hasPart, Phoenix Settlement]
  • A. Phoenix Settlement chosen
    Phoenix Settlement is a historic communal farm near Durban, South Africa, founded by Mahatma Gandhi in 1904 as a base for his experiments in simple living and satyagraha.
  • B. Crotonville
    Crotonville is a small hamlet within the town of Ossining in Westchester County, New York.
  • C. Centinel
    Centinel was the pseudonym used by a prominent Anti-Federalist writer who authored influential essays opposing the ratification of the U.S. Constitution in the late 1780s.
  • D. Pennyville
    Pennyville is the historic former name of what is now the Chicago suburb of Park Ridge, Illinois.
  • E. Crescent Town
    Crescent Town is a densely populated, multicultural residential neighbourhood in Toronto, Ontario, known for its high-rise apartment complexes and proximity to public transit.
  • 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_69bd443e941881908eb4e8c685b6f656 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75219a94819094fc54c1df448470 completed March 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb13fd3a88190b5a665ba56fdd455 completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:40 p.m.