Triple

T27353290
Position Surface form Disambiguated ID Type / Status
Subject Peak Tower E685618 entity
Predicate hasTicketedArea P174346 FINISHED
Object Sky Terrace 428 observation deck
Sky Terrace 428 observation deck is a popular open-air viewing platform on Hong Kong’s Victoria Peak offering panoramic views of the city skyline and harbor.
 E1769023 NE FINISHED

How this triple was built (3 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: Sky Terrace 428 observation deck | Statement: [Peak Tower, hasTicketedArea, Sky Terrace 428 observation deck]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sky Terrace 428 observation deck
Triple: [Peak Tower, hasTicketedArea, Sky Terrace 428 observation deck]
Generated description
Sky Terrace 428 observation deck is a popular open-air viewing platform on Hong Kong’s Victoria Peak offering panoramic views of the city skyline and harbor.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasTicketedArea
Context triple: [Peak Tower, hasTicketedArea, Sky Terrace 428 observation deck]
  • A. hasTicketCollectorArea
    Indicates that a location or facility includes a designated area where ticket collectors operate or perform their duties.
  • B. hasTicket
    Indicates that an entity possesses or holds a ticket, typically granting access, entry, or a right to a service or event.
  • C. hasTicketAccess
    Indicates that an entity is permitted to view, use, or manage a particular ticket or set of tickets.
  • D. hasTicketRequirement
    Indicates that an entity is subject to a specific ticket or admission requirement in order for access, participation, or use to be allowed.
  • E. hasTicketHall
    Indicates that a place or facility includes or is equipped with a designated ticket hall area for purchasing or validating tickets.
  • F. None of above. chosen

Provenance (7 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_69ef14887c288190931b8431fdbf53c4 completed April 27, 2026, 7:47 a.m.
NER Named-entity recognition batch_69f6c20f209081909fb9ac8f95069f04 completed May 3, 2026, 3:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a12a7d4786c8190881df8e944b7f868 completed May 24, 2026, 7:25 a.m.
NEDg Description generation batch_6a12a8b8ec608190846c55dabeec801a completed May 24, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_6a12a951f04881909419d5b9d41d5c79 completed May 24, 2026, 7:31 a.m.
PD Predicate disambiguation batch_69f6bd2415fc81908c23c311aebce66f completed May 3, 2026, 3:12 a.m.
PDg Predicate description generation batch_69f6c125695c81909704c67bef4ce5b2 completed May 3, 2026, 3:29 a.m.
Created at: April 27, 2026, 11:49 a.m.