Triple

T19193841
Position Surface form Disambiguated ID Type / Status
Subject Stung Treng E469912 entity
Predicate governingCountryCapital P204 FINISHED
Object Phnom Penh 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: Phnom Penh | Statement: [Stung Treng, governingCountryCapital, Phnom Penh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phnom Penh
Context triple: [Stung Treng, governingCountryCapital, Phnom Penh]
  • A. Phnom Penh chosen
    Phnom Penh is the capital and largest city of Cambodia, known for its location at the confluence of the Mekong and Tonlé Sap rivers and its blend of French colonial and Khmer architecture.
  • B. Phonsavan
    Phonsavan is a town in central Laos that serves as the main gateway and service hub for visitors to the historic and mysterious Plain of Jars archaeological site.
  • C. Krong Reap
    Krong Reap is the primary demon antagonist in the Khmer epic Reamker, the Cambodian adaptation of the Ramayana.
  • D. Vientiane
    Vientiane is the capital and largest city of Laos, situated along the Mekong River near the border with Thailand.
  • E. Sihanoukville
    Sihanoukville is a coastal city in southwestern Cambodia known for its beaches, port facilities, and role as a growing tourism and commercial hub.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a409948190a17aa28a6e9c8844 completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.