Triple

T30858120
Position Surface form Disambiguated ID Type / Status
Subject The Girl on the Front Page (1936 film) E785984 entity
Predicate title P38 FINISHED
Object The Girl on the Front Page
The Girl on the Front Page is a 1936 American comedy film centered on the fast-paced, often chaotic world of newspaper journalism.
E1933793 NE FINISHED

How this triple was built (2 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: The Girl on the Front Page | Statement: [The Girl on the Front Page (1936 film), title, The Girl on the Front Page]
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: The Girl on the Front Page
Triple: [The Girl on the Front Page (1936 film), title, The Girl on the Front Page]
Generated description
The Girl on the Front Page is a 1936 American comedy film centered on the fast-paced, often chaotic world of newspaper journalism.

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_69f224b91c14819084e764832fe67a57 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f691a665c481908e0a9a2aef659563 completed May 3, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a28bbfe19c4819087fad1ea3f0e9022 completed June 10, 2026, 1:21 a.m.
NEDg Description generation batch_6a28bdd1e710819082b91a81919fd034 completed June 10, 2026, 1:28 a.m.
NED2 Entity disambiguation (via description) batch_6a28be41f5548190b09cc744556eb9e4 completed June 10, 2026, 1:30 a.m.
Created at: April 29, 2026, 8:46 p.m.