Triple

T8515566
Position Surface form Disambiguated ID Type / Status
Subject Sandra Bullock E201563 entity
Predicate notableWork P4 FINISHED
Object The Lost City E263951 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: The Lost City | Statement: [Sandra Bullock, notableWork, The Lost City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Lost City
Context triple: [Sandra Bullock, notableWork, The Lost City]
  • A. The Lost City chosen
    The Lost City is a 2005 drama film directed by and starring Andy García that portrays a Cuban nightclub owner's struggles amid the Cuban Revolution and the rise of Fidel Castro.
  • B. Lost City
    Lost City is an ancient-civilization-themed area at Thorpe Park featuring several of the park’s major thrill rides and attractions.
  • C. Lost City
    Lost City is an adventure-themed zone within the Trans Studio Makassar indoor amusement park, featuring attractions and rides inspired by exploration and ancient civilizations.
  • D. The Lost Continent
    The Lost Continent is a mythically themed land at Universal's Islands of Adventure, featuring attractions and environments inspired by ancient legends and lost civilizations.
  • E. Capital of the Ruins
    Capital of the Ruins is the wartime nickname of the heavily devastated French town of Saint-Lô, reflecting the extensive destruction it suffered during World War II.
  • 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_69ca8320e5748190ac2c585a0bba8193 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe60f37b0819082ae14e539f57b56 completed March 31, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4e5dbb3c81909157e6b04a4956af completed April 2, 2026, 11:09 a.m.
Created at: March 30, 2026, 6:15 p.m.