Triple

T1293783
Position Surface form Disambiguated ID Type / Status
Subject Mount Lee E27606 entity
Predicate overlooks P1323 FINISHED
Object Hollywood Sign E1427 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: Hollywood Sign | Statement: [Mount Lee, overlooks, Hollywood Sign]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hollywood Sign
Context triple: [Mount Lee, overlooks, Hollywood Sign]
  • A. Hollywood Sign chosen
    The Hollywood Sign is an iconic hillside landmark in Los Angeles that symbolizes the American film industry and global entertainment culture.
  • B. California Tower
    California Tower is a historic Spanish-Colonial Revival bell tower and prominent architectural landmark located in Balboa Park, San Diego.
  • C. Los Angeles City Hall
    Los Angeles City Hall is the historic and iconic main municipal building of Los Angeles, housing the mayor’s office and the city council chambers.
  • D. Santa Monica Pier
    The Santa Monica Pier is a historic oceanfront landmark featuring an amusement park, restaurants, and an iconic Ferris wheel extending over the Pacific Ocean.
  • E. Hollywood Walk of Fame
    The Hollywood Walk of Fame is a famous sidewalk attraction in Los Angeles featuring embedded stars honoring notable figures from the entertainment industry.
  • 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_69a496d6682881909ba658f1c1e0e2b0 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c0f2eb608190a0ac47a73adae19b completed March 1, 2026, 10:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69acacc1e7948190a1ecd240c751d258 completed March 7, 2026, 10:54 p.m.
Created at: March 1, 2026, 7:51 p.m.