Triple

T23897648
Position Surface form Disambiguated ID Type / Status
Subject Teresa Lisbon E600948 entity
Predicate memberOf P10 FINISHED
Object CBI Serious Crimes Unit
The CBI Serious Crimes Unit is a specialized investigative division in the TV series "The Mentalist" that handles high-profile and complex criminal cases for the California Bureau of Investigation.
E1608572 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: CBI Serious Crimes Unit | Statement: [Teresa Lisbon, memberOf, CBI Serious Crimes Unit]
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: CBI Serious Crimes Unit
Triple: [Teresa Lisbon, memberOf, CBI Serious Crimes Unit]
Generated description
The CBI Serious Crimes Unit is a specialized investigative division in the TV series "The Mentalist" that handles high-profile and complex criminal cases for the California Bureau of Investigation.

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_69e295341ac0819080647f2908af793c completed April 17, 2026, 8:16 p.m.
NER Named-entity recognition batch_69f1cddb3fdc819096dc84a1774d9bee completed April 29, 2026, 9:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f762aaf588190aba5f0757ac0bfaa completed May 21, 2026, 9:16 p.m.
NEDg Description generation batch_6a0f7721b65481908b58b4d68e50768c completed May 21, 2026, 9:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0f7893346c81908879db417e4854d1 completed May 21, 2026, 9:26 p.m.
Created at: April 17, 2026, 8:25 p.m.