Triple

T11153950
Position Surface form Disambiguated ID Type / Status
Subject Kempten E263855 entity
Predicate hasHistoricalName P2834 FINISHED
Object Cambodunum E251415 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: Cambodunum | Statement: [Kempten, hasHistoricalName, Cambodunum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cambodunum
Context triple: [Kempten, hasHistoricalName, Cambodunum]
  • A. Cambodunum chosen
    Cambodunum was a major Roman settlement and administrative center in the province of Raetia, located near present-day Kempten in southern Germany.
  • B. Kambojas
    The Kambojas were an ancient Indo-Iranian people mentioned in Indian and Persian sources, known for their warrior traditions and presence in regions around present-day Afghanistan and northwestern South Asia.
  • C. Kambos
    Kambos is a coastal village on the Greek island of Patmos, known for its sandy beach and role as a popular summer resort area.
  • D. Kambo
    Kambo is a small village and residential area in Moss municipality in southeastern Norway.
  • E. Cambodia
    Cambodia is a Southeast Asian nation known for its ancient Khmer civilization, the Angkor Wat temple complex, and a modern history marked by French colonial rule and the Khmer Rouge regime.
  • 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_69d6aa9ccddc8190868998c8b7beb060 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e872ffbc8190b8a3bbd912115342 completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69e46341f224819099dd618b377e5bc2 completed April 19, 2026, 5:08 a.m.
Created at: April 8, 2026, 9:28 p.m.