Triple

T22021043
Position Surface form Disambiguated ID Type / Status
Subject Doug Liman E543846 entity
Predicate familyName P18 FINISHED
Object Liman 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: Liman | Statement: [Doug Liman, familyName, Liman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liman
Context triple: [Doug Liman, familyName, Liman]
  • A. Liman chosen
    Liman is a surname most notably associated with American film director and producer Doug Liman.
  • B. Alushta
    Alushta is a resort town on the southern coast of Crimea, known for its beaches, mild climate, and role as a popular Black Sea tourist destination.
  • C. Sasa Port
    Sasa Port is a major seaport and cargo gateway serving Davao City and the surrounding region in southeastern Mindanao, Philippines.
  • D. Sovetskaya Gavan
    Sovetskaya Gavan is a port town on the Strait of Tartary in Russia’s Far East, serving as an important maritime and transport hub in Khabarovsk Krai.
  • E. Yalta Sea Port
    Yalta Sea Port is a major maritime harbor and transportation hub serving the resort city of Yalta on the southern coast of the Crimean Peninsula.
  • 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127c7b3308190ac056bef6f82722e completed April 28, 2026, 9:33 p.m.
Created at: April 16, 2026, 8:23 p.m.