Triple

T27279418
Position Surface form Disambiguated ID Type / Status
Subject The Isle of Lost Ships E688288 entity
Predicate screenwriter P2831 FINISHED
Object John Gilbert
John Gilbert was a prominent American silent film actor and occasional screenwriter, celebrated as one of MGM’s biggest romantic leading men of the 1920s.
 E430893 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: John Gilbert | Statement: [The Isle of Lost Ships, screenwriter, John Gilbert]
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: John Gilbert
Triple: [The Isle of Lost Ships, screenwriter, John Gilbert]
Generated description
John Gilbert was a prominent American silent film actor and occasional screenwriter, celebrated as one of MGM’s biggest romantic leading men of the 1920s.

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_69ef3558cf8881909595ef89daf6e14a completed April 27, 2026, 10:07 a.m.
NER Named-entity recognition batch_69f6272c4eb081909b224d630b7c48d6 completed May 2, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a129ca187888190aaaa87340451a4b9 completed May 24, 2026, 6:37 a.m.
NEDg Description generation batch_6a129e0722388190bce1a8749df3f7bf completed May 24, 2026, 6:43 a.m.
NED2 Entity disambiguation (via description) batch_6a129e7b3f508190b7cc7b6f40177927 completed May 24, 2026, 6:45 a.m.
Created at: April 27, 2026, 11:05 a.m.