Triple

T33906370
Position Surface form Disambiguated ID Type / Status
Subject Linda Cardellini as Lindsay Weir E869191 entity
Predicate formerFriendGroup P170326 FINISHED
Object Millie Kentner
Millie Kentner is a devout, academically focused teenager and Lindsay Weir’s former best friend in the TV series "Freaks and Geeks."
 E2072714 NE FINISHED

How this triple was built (3 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: Millie Kentner | Statement: [Linda Cardellini as Lindsay Weir, formerFriendGroup, Millie Kentner]
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: Millie Kentner
Triple: [Linda Cardellini as Lindsay Weir, formerFriendGroup, Millie Kentner]
Generated description
Millie Kentner is a devout, academically focused teenager and Lindsay Weir’s former best friend in the TV series "Freaks and Geeks."
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: formerFriendGroup
Context triple: [Linda Cardellini as Lindsay Weir, formerFriendGroup, Millie Kentner]
  • A. formerFriend chosen
    Indicates that two entities were once friends but are no longer in a friendship relationship.
  • B. childhoodFriend
    Indicates that two people were close friends during their childhood period.
  • C. friendAndTeammate
    Indicates that one entity has a relationship with another in which they are both friends and members of the same team.
  • D. relationshipToFriends
    Indicates the type or nature of the relationship an entity has with its friends.
  • E. formedGroup
    Indicates that multiple entities have come together to create or establish a group or collective unit.
  • F. None of above.

Provenance (6 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_69f34997703c8190866b1d404bce531f completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69ffe23081408190a121d901dbce1403 completed May 10, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a368245e0588190a71829ba452c622e completed June 20, 2026, 12:06 p.m.
NEDg Description generation batch_6a3682cb71688190a91c1b9ecba2c37f completed June 20, 2026, 12:08 p.m.
NED2 Entity disambiguation (via description) batch_6a368327e7248190801ee93ba760d704 completed June 20, 2026, 12:10 p.m.
PD Predicate disambiguation batch_69ffe18aed348190912a5996b2da728b completed May 10, 2026, 1:38 a.m.
Created at: May 1, 2026, 1:48 a.m.