Triple

T6167675
Position Surface form Disambiguated ID Type / Status
Subject Erle Stanley Gardner E137609 entity
Predicate givenName P17 FINISHED
Object Erle
Erle is the given name of Erle Stanley Gardner, the American lawyer and prolific author best known for creating the fictional defense attorney Perry Mason.
 E572513 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: Erle | Statement: [Erle Stanley Gardner, givenName, Erle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Erle
Context triple: [Erle Stanley Gardner, givenName, Erle]
  • A. Erlich
    Erlich is a variant spelling of the surname Ehrlich, which is of German origin and commonly associated with Jewish families.
  • B. Esselen
    Esselen is a nearly extinct Native American language once spoken by the Esselen people of the central California coast.
  • C. Elatus
    Elatus is a figure from Greek mythology, known as a son of the Muse Erato and associated with various minor mythic traditions.
  • D. Troulos
    Troulos is a small coastal village and popular beach resort on the Greek island of Skiathos in the Sporades.
  • E. Dromi
    Dromi is a mythical chain in Norse mythology that was used in an early attempt to bind the monstrous wolf Fenrir.
  • 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: Erle
Triple: [Erle Stanley Gardner, givenName, Erle]
Generated description
Erle is the given name of Erle Stanley Gardner, the American lawyer and prolific author best known for creating the fictional defense attorney Perry Mason.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Erle
Target entity description: Erle is the given name of Erle Stanley Gardner, the American lawyer and prolific author best known for creating the fictional defense attorney Perry Mason.
  • A. Erlich
    Erlich is a variant spelling of the surname Ehrlich, which is of German origin and commonly associated with Jewish families.
  • B. Esselen
    Esselen is a nearly extinct Native American language once spoken by the Esselen people of the central California coast.
  • C. Elatus
    Elatus is a figure from Greek mythology, known as a son of the Muse Erato and associated with various minor mythic traditions.
  • D. Troulos
    Troulos is a small coastal village and popular beach resort on the Greek island of Skiathos in the Sporades.
  • E. Dromi
    Dromi is a mythical chain in Norse mythology that was used in an early attempt to bind the monstrous wolf Fenrir.
  • F. None of above. chosen

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_69c008a68c508190a8d78245c865960e completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05d647ae48190a1db07b4f4a06e67 completed March 22, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141a3ea6c81908847998960c9d0eb completed March 23, 2026, 1:35 p.m.
NEDg Description generation batch_69c143d8090081909ec2759a7025bcfb completed March 23, 2026, 1:44 p.m.
NED2 Entity disambiguation (via description) batch_69c1444a09ac8190acfee8a878652d16 completed March 23, 2026, 1:46 p.m.
Created at: March 22, 2026, 4:17 p.m.