Triple

T20011459
Position Surface form Disambiguated ID Type / Status
Subject Hamnet E494599 entity
Predicate publisher P29 FINISHED
Object Tinder Press
Tinder Press is a literary imprint of Headline Publishing Group known for publishing high-quality, critically acclaimed fiction.
E1405124 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: Tinder Press | Statement: [Hamnet, publisher, Tinder Press]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tinder Press
Context triple: [Hamnet, publisher, Tinder Press]
  • A. Matchmakers
    Matchmakers is a popular Ukrainian comedy television series produced by Kvartal 95 Studio that follows the humorous clashes and relationships between two very different families.
  • B. Lovehunter
    Lovehunter is a 1979 hard rock album by British band Whitesnake, noted for its bluesy sound and controversial cover art.
  • C. The MatchMaker
    The MatchMaker is a romantic comedy film best known for its lighthearted story about love and relationships, released in the late 1990s.
  • D. Match.com
    Match.com is one of the earliest and most prominent online dating services, connecting singles worldwide through its web and mobile platforms.
  • E. Hinge
    Hinge is a dating app designed to foster serious, long-term relationships by encouraging users to build detailed profiles and engage in more meaningful conversations.
  • 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: Tinder Press
Triple: [Hamnet, publisher, Tinder Press]
Generated description
Tinder Press is a literary imprint of Headline Publishing Group known for publishing high-quality, critically acclaimed fiction.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tinder Press
Target entity description: Tinder Press is a literary imprint of Headline Publishing Group known for publishing high-quality, critically acclaimed fiction.
  • A. Matchmakers
    Matchmakers is a popular Ukrainian comedy television series produced by Kvartal 95 Studio that follows the humorous clashes and relationships between two very different families.
  • B. Lovehunter
    Lovehunter is a 1979 hard rock album by British band Whitesnake, noted for its bluesy sound and controversial cover art.
  • C. The MatchMaker
    The MatchMaker is a romantic comedy film best known for its lighthearted story about love and relationships, released in the late 1990s.
  • D. Match.com
    Match.com is one of the earliest and most prominent online dating services, connecting singles worldwide through its web and mobile platforms.
  • E. Hinge
    Hinge is a dating app designed to foster serious, long-term relationships by encouraging users to build detailed profiles and engage in more meaningful conversations.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623773d88190826616a02d3c3e69 completed April 20, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0805137f2081908f63e0ab7fe5d3d4 completed May 16, 2026, 5:48 a.m.
NEDg Description generation batch_6a08056969748190aeddd8a11f6904cd completed May 16, 2026, 5:49 a.m.
NED2 Entity disambiguation (via description) batch_6a0805f206748190845ab7eb7042d679 completed May 16, 2026, 5:51 a.m.
Created at: April 11, 2026, 3:33 p.m.