Triple

T17816618
Position Surface form Disambiguated ID Type / Status
Subject Emily Beecham E444861 entity
Predicate filmographyIncludes P15620 FINISHED
Object Daphne
"Daphne" is a 2017 British drama film starring Emily Beecham as a sharp-witted but emotionally adrift London woman confronting a personal crisis.
 E1290163 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: Daphne | Statement: [Emily Beecham, filmographyIncludes, Daphne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Daphne
Context triple: [Emily Beecham, filmographyIncludes, Daphne]
  • A. Daphne
    Daphne is a nymph from Greek mythology best known for being pursued by Apollo and transformed into a laurel tree to escape him.
  • B. Daphne
    Daphne is a coastal city in Baldwin County, Alabama, situated along the eastern shore of Mobile Bay.
  • C. Daphne
    "Daphne" is a fast, swinging jazz composition by guitarist Django Reinhardt that has become a recognized standard in the gypsy jazz repertoire.
  • D. Daphne
    Daphne is an HTTP, HTTP/2, and WebSocket server for ASGI applications, commonly used to serve Django and other Python async web frameworks.
  • E. Daphne
    Daphne is the nickname of Dorothy de Sélincourt, an English editor and the wife of author A. A. Milne.
  • 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: Daphne
Triple: [Emily Beecham, filmographyIncludes, Daphne]
Generated description
"Daphne" is a 2017 British drama film starring Emily Beecham as a sharp-witted but emotionally adrift London woman confronting a personal crisis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Daphne
Target entity description: "Daphne" is a 2017 British drama film starring Emily Beecham as a sharp-witted but emotionally adrift London woman confronting a personal crisis.
  • A. Daphne chosen
    Daphne is a 2017 British drama film starring Emily Beecham as a sharp-tongued, disaffected Londoner whose life begins to unravel after she witnesses a violent incident.
  • B. Daphne
    Daphne is a nymph from Greek mythology best known for being pursued by Apollo and transformed into a laurel tree to escape him.
  • C. Daphne
    Daphne is the nickname of Dorothy de Sélincourt, an English editor and the wife of author A. A. Milne.
  • D. Daphne
    Daphne is a coastal city in Baldwin County, Alabama, situated along the eastern shore of Mobile Bay.
  • E. Daphne
    "Daphne" is a fast, swinging jazz composition by guitarist Django Reinhardt that has become a recognized standard in the gypsy jazz repertoire.
  • F. None of above.

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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4887f7d048190b6d813b9f0fab3e7 completed April 19, 2026, 7:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0306ef9e6c819083d42f2f4fb27880 completed May 12, 2026, 10:54 a.m.
NEDg Description generation batch_6a03075d0df4819093e20f299f0824a8 completed May 12, 2026, 10:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0307c1a95881909547178762490619 completed May 12, 2026, 10:58 a.m.
Created at: April 10, 2026, 10:14 a.m.