Triple

T35537624
Position Surface form Disambiguated ID Type / Status
Subject Caveman (GEICO Cavemen) E1026971 entity
Predicate portrayedBy P1507 FINISHED
Object Jeff Daniel Phillips
Jeff Daniel Phillips is an American actor and filmmaker best known for playing one of the GEICO Cavemen and for his frequent collaborations with director Rob Zombie in horror films and television projects.
E2144057 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: Jeff Daniel Phillips | Statement: [Caveman (GEICO Cavemen), portrayedBy, Jeff Daniel Phillips]
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: Jeff Daniel Phillips
Triple: [Caveman (GEICO Cavemen), portrayedBy, Jeff Daniel Phillips]
Generated description
Jeff Daniel Phillips is an American actor and filmmaker best known for playing one of the GEICO Cavemen and for his frequent collaborations with director Rob Zombie in horror films and television projects.

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_69f76dff7e508190b28ceeee770dce23 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f79802a8d48190ac5ba33aae14f1f8 completed May 3, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a384a4cfcf4819084b4ce6c8b55d16e completed June 21, 2026, 8:32 p.m.
NEDg Description generation batch_6a384ad781b48190b37e3ae4708eae57 completed June 21, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_6a384b6644208190b1c18024a063846b completed June 21, 2026, 8:36 p.m.
Created at: May 3, 2026, 4:04 p.m.