Triple

T23426692
Position Surface form Disambiguated ID Type / Status
Subject Dedinje E560812 entity
Predicate hasLandmark P105 FINISHED
Object White Palace 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: White Palace | Statement: [Dedinje, hasLandmark, White Palace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: White Palace
Context triple: [Dedinje, hasLandmark, White Palace]
  • A. White Palace
    White Palace is a 1990 romantic drama film starring Susan Sarandon and James Spader, known for its exploration of a passionate relationship that crosses class and age boundaries.
  • B. White Palace chosen
    White Palace is a royal residence in Belgrade’s Dedinje district, historically used by the Yugoslav and later Serbian royal family for official and ceremonial functions.
  • C. White Palace
    White Palace is a prominent royal residence within Tehran’s Sa’dabad Complex, historically used by Iran’s Pahlavi dynasty as an official palace.
  • D. White Palace
    White Palace is the residential and administrative section of Lhasa’s Potala Palace complex, historically serving as the living quarters and governmental center of the Dalai Lamas.
  • E. White Palace
    White Palace is a museum, formally known as the Museum of Nations, that showcases cultural and historical exhibits.
  • 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_69e2454cb1108190ab21ada5411a7146 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a54a28a08190add6184a44c5005b completed April 29, 2026, 6:29 a.m.
Created at: April 17, 2026, 5:47 p.m.