Triple

T36720096
Position Surface form Disambiguated ID Type / Status
Subject Caroline Dhavernas E907031 entity
Predicate playedCharacter P1507 FINISHED
Object Dr. Alana Bloom
Dr. Alana Bloom is a compassionate FBI consultant and psychology professor in the TV series "Hannibal," known for her ethical stance and complex relationships with the show's central characters.
E2195368 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: Dr. Alana Bloom | Statement: [Caroline Dhavernas, playedCharacter, Dr. Alana Bloom]
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: Dr. Alana Bloom
Triple: [Caroline Dhavernas, playedCharacter, Dr. Alana Bloom]
Generated description
Dr. Alana Bloom is a compassionate FBI consultant and psychology professor in the TV series "Hannibal," known for her ethical stance and complex relationships with the show's central characters.

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_69f76e746e4c8190a0d05cc6d57a643e completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7c84319dc8190987c08469720d6b1 completed May 3, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3a38376c188190871e7fb00dbe8a64 completed June 23, 2026, 7:39 a.m.
NEDg Description generation batch_6a3a38cef65c8190a4c5dafe793fcf7c completed June 23, 2026, 7:42 a.m.
NED2 Entity disambiguation (via description) batch_6a3a3a51dabc81909cf57f44ec196576 completed June 23, 2026, 7:48 a.m.
Created at: May 3, 2026, 4:12 p.m.