Triple

T10514622
Position Surface form Disambiguated ID Type / Status
Subject Adam Shankman E248000 entity
Predicate familyName P18 FINISHED
Object Shankman
Shankman is a surname most notably associated with American film director and choreographer Adam Shankman.
 E868270 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: Shankman | Statement: [Adam Shankman, familyName, Shankman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shankman
Context triple: [Adam Shankman, familyName, Shankman]
  • A. Shawbost
    Shawbost is a village on the west coast of the Isle of Lewis in Scotland’s Outer Hebrides, known for its Gaelic heritage and coastal scenery.
  • B. Stockach
    Stockach is a small town in southern Germany’s Baden-Württemberg state, situated near Lake Constance and known historically as a regional administrative and market center.
  • C. The Joe
    The Joe is a famous indoor arena in Detroit, Michigan, best known as the longtime home of the NHL’s Detroit Red Wings.
  • D. Fink
    Fink is a British singer-songwriter and producer known for his atmospheric blend of folk, blues, and electronic music.
  • E. Fink
    Fink is an open-source package management system that brings a wide range of Unix and open-source software to macOS by compiling and distributing it in a convenient, Debian-like format.
  • 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: Shankman
Triple: [Adam Shankman, familyName, Shankman]
Generated description
Shankman is a surname most notably associated with American film director and choreographer Adam Shankman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shankman
Target entity description: Shankman is a surname most notably associated with American film director and choreographer Adam Shankman.
  • A. Shawbost
    Shawbost is a village on the west coast of the Isle of Lewis in Scotland’s Outer Hebrides, known for its Gaelic heritage and coastal scenery.
  • B. Stockach
    Stockach is a small town in southern Germany’s Baden-Württemberg state, situated near Lake Constance and known historically as a regional administrative and market center.
  • C. The Joe
    The Joe is a famous indoor arena in Detroit, Michigan, best known as the longtime home of the NHL’s Detroit Red Wings.
  • D. Fink
    Fink is a British singer-songwriter and producer known for his atmospheric blend of folk, blues, and electronic music.
  • E. Fink
    Fink is an open-source package management system that brings a wide range of Unix and open-source software to macOS by compiling and distributing it in a convenient, Debian-like format.
  • 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_69d381c4aa948190942e1d803143fb0e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509cade0c81908fcbd54a90106bf9 completed April 7, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90df141488190a2674546aa437de8 completed April 10, 2026, 2:49 p.m.
NEDg Description generation batch_69d9107dc8448190998c4044f68a775e completed April 10, 2026, 3 p.m.
NED2 Entity disambiguation (via description) batch_69d911e7d2dc8190a67b2513607fdf98 completed April 10, 2026, 3:06 p.m.
Created at: April 6, 2026, 12:27 p.m.