Triple

T25936778
Position Surface form Disambiguated ID Type / Status
Subject Clarke Griffin E653582 entity
Predicate father P120 FINISHED
Object Jake Griffin
Jake Griffin is a character from the television series "The 100," known as Clarke Griffin’s idealistic engineer father who challenges the Ark’s leadership and is executed for attempting to expose their secrets.
E1705576 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: Jake Griffin | Statement: [Clarke Griffin, father, Jake Griffin]
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: Jake Griffin
Triple: [Clarke Griffin, father, Jake Griffin]
Generated description
Jake Griffin is a character from the television series "The 100," known as Clarke Griffin’s idealistic engineer father who challenges the Ark’s leadership and is executed for attempting to expose their secrets.

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_69e7ab3fd2f881908837305e4ba98011 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f6041dd44c8190b96a3cac660e295a completed May 2, 2026, 2:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1107745e248190890a67b6627831a4 completed May 23, 2026, 1:48 a.m.
NEDg Description generation batch_6a11082bcf9c8190a80f0ed23b79a823 completed May 23, 2026, 1:51 a.m.
NED2 Entity disambiguation (via description) batch_6a110c2ac828819088a7a9feb579e6e6 completed May 23, 2026, 2:08 a.m.
Created at: April 22, 2026, 8:39 a.m.