Triple

T25905209
Position Surface form Disambiguated ID Type / Status
Subject The Navigator E652732 entity
Predicate writer P1360 FINISHED
Object Jean C. Havez
Jean C. Havez was an American screenwriter and humorist best known for his work on silent film comedies, including collaborations with Buster Keaton.
E1701086 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: Jean C. Havez | Statement: [The Navigator, writer, Jean C. Havez]
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: Jean C. Havez
Triple: [The Navigator, writer, Jean C. Havez]
Generated description
Jean C. Havez was an American screenwriter and humorist best known for his work on silent film comedies, including collaborations with Buster Keaton.

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_69e7ab3d3f8481909bc53ed64c06af33 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f603beb5248190aed52bf4e44f223c completed May 2, 2026, 2:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10ecc7ce408190b249032a85822718 completed May 22, 2026, 11:54 p.m.
NEDg Description generation batch_6a10edf7ff0c8190935a637ff0df364b completed May 22, 2026, 11:59 p.m.
NED2 Entity disambiguation (via description) batch_6a10ef6795e08190a1ba5f600628316b completed May 23, 2026, 12:05 a.m.
Created at: April 22, 2026, 8:27 a.m.