Triple

T3050573
Position Surface form Disambiguated ID Type / Status
Subject Bravo E83558 entity
Predicate hasFranchise P13614 FINISHED
Object Below Deck
Below Deck is a reality television series that follows the lives and work of crew members aboard luxury yachts as they cater to demanding charter guests.
E322207 NE FINISHED

How this triple was built (4 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: Below Deck | Statement: [Bravo, hasFranchise, Below Deck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Below Deck
Context triple: [Bravo, hasFranchise, Below Deck]
  • A. Inspectah Deck
    Inspectah Deck is an American rapper and producer best known as a core member and sharp-lyricist of the influential hip hop group Wu-Tang Clan.
  • B. Above the Dock
    "Above the Dock" is a brief imagist poem by T. E. Hulme that vividly captures a nighttime urban scene through precise, economical imagery.
  • C. Flight Deck
    Flight Deck is a steel inverted roller coaster at Canada's Wonderland themed around fighter jets and known for its intense, looping layout.
  • D. Subsurface
    Subsurface is an open-source dive log and planning software application originally developed by Linux creator Linus Torvalds for recreational and technical scuba divers.
  • E. Bovenden
    Bovenden is a municipality in Lower Saxony, Germany, situated just north of the city of Göttingen.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Below Deck
Triple: [Bravo, hasFranchise, Below Deck]
Generated description
Below Deck is a reality television series that follows the lives and work of crew members aboard luxury yachts as they cater to demanding charter guests.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Below Deck
Target entity description: Below Deck is a reality television series that follows the lives and work of crew members aboard luxury yachts as they cater to demanding charter guests.
  • A. Inspectah Deck
    Inspectah Deck is an American rapper and producer best known as a core member and sharp-lyricist of the influential hip hop group Wu-Tang Clan.
  • B. Above the Dock
    "Above the Dock" is a brief imagist poem by T. E. Hulme that vividly captures a nighttime urban scene through precise, economical imagery.
  • C. Flight Deck
    Flight Deck is a steel inverted roller coaster at Canada's Wonderland themed around fighter jets and known for its intense, looping layout.
  • D. Subsurface
    Subsurface is an open-source dive log and planning software application originally developed by Linux creator Linus Torvalds for recreational and technical scuba divers.
  • E. Bovenden
    Bovenden is a municipality in Lower Saxony, Germany, situated just north of the city of Göttingen.
  • F. None of above. chosen

Provenance (5 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_69ad8b24924c8190a9bb6f61d519e4ae completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9bb1a46081908547a2f27cbf3446 completed March 8, 2026, 3:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1eefa84f08190a178cc0674d8a3ab completed March 11, 2026, 10:38 p.m.
NEDg Description generation batch_69b1ef69d49c81908caa41a80718896b completed March 11, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69b1f05e44e08190be8b194938b6c1c7 completed March 11, 2026, 10:44 p.m.
Created at: March 8, 2026, 3:01 p.m.