Triple

T29691906
Position Surface form Disambiguated ID Type / Status
Subject Betty Compson E751230 entity
Predicate notableWork P4 FINISHED
Object The Woman with Four Faces
The Woman with Four Faces is a 1923 silent crime drama film starring Betty Compson as a master of disguise entangled in underworld intrigue.
 E1878283 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 Woman with Four Faces | Statement: [Betty Compson, notableWork, The Woman with Four Faces]
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 Woman with Four Faces
Triple: [Betty Compson, notableWork, The Woman with Four Faces]
Generated description
The Woman with Four Faces is a 1923 silent crime drama film starring Betty Compson as a master of disguise entangled in underworld intrigue.

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_69f0d625b09481909b0b69aea1e846c8 completed April 28, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f6729570ac819095ce1c4e2ffd5971 completed May 2, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a267ecc4ef8819080c42b27e0d200af completed June 8, 2026, 8:35 a.m.
NEDg Description generation batch_6a26832a8e748190a3c1f1aded457b04 completed June 8, 2026, 8:54 a.m.
NED2 Entity disambiguation (via description) batch_6a2683c29a2481908b77b234a551c370 completed June 8, 2026, 8:56 a.m.
Created at: April 28, 2026, 7:17 p.m.