Triple

T9362488
Position Surface form Disambiguated ID Type / Status
Subject 1937 Columbus Platform E225313 entity
Predicate title P38 FINISHED
Object Columbus Platform E44178 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: Columbus Platform | Statement: [1937 Columbus Platform, title, Columbus Platform]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Columbus Platform
Context triple: [1937 Columbus Platform, title, Columbus Platform]
  • A. Columbus Platform chosen
    The Columbus Platform is a 1937 statement of principles that marked a major shift in Reform Judaism toward greater appreciation of Jewish peoplehood, tradition, and Zionism.
  • B. Cordova
    Cordova is a coastal municipality in Cebu, Philippines, located on Mactan Island and known for its mangrove forests, marine sanctuaries, and growing tourism industry.
  • C. Cordova
    Cordova is a small coastal town in south-central Alaska known for its fishing industry, remote setting, and proximity to the Chugach National Forest and Prince William Sound.
  • D. Embarcadero
    Embarcadero is a historic waterfront district in San Francisco known for its piers, ferry terminal, and scenic promenade along the bay.
  • E. Zeta platform
    Zeta platform is a General Motors-developed digital vehicle software and connectivity platform designed to power in-car services, data, and user experiences.
  • 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_69ca842bdd648190904131d58620d448 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd503ca7308190818f27f1faf94a53 completed April 1, 2026, 5:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0f3eaf2208190967a3a8e82a4070b completed April 4, 2026, 11:20 a.m.
Created at: March 30, 2026, 7:42 p.m.