Triple

T9690550
Position Surface form Disambiguated ID Type / Status
Subject The Last of Us Part II E234523 entity
Predicate character P662 FINISHED
Object Lev
Lev is a young, brave former Seraphite who becomes a key companion to Abby in The Last of Us Part II, known for his resilience, archery skills, and struggle against his sect’s rigid beliefs.
 E815685 NE FINISHED

How this triple was built (4 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: Lev | Statement: [The Last of Us Part II, character, Lev]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lev
Context triple: [The Last of Us Part II, character, Lev]
  • A. Lev
    Lev is the Russian given name of the renowned writer Leo Tolstoy, under which he was known in his native language.
  • B. Leonid
    Leonid is a masculine given name of Slavic origin, notably borne by Soviet leader Leonid Brezhnev.
  • C. Levin
    Levin is a surname of Jewish origin borne by various notable individuals across fields such as business, politics, and the arts.
  • D. Levin
    Levin is a town in New Zealand’s North Island known as a service and retail hub for the surrounding agricultural Horowhenua district.
  • E. Levin
    Levin is a masculine given name of Germanic origin, historically borne by figures such as the Russian general Levin August von Bennigsen.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Lev
Triple: [The Last of Us Part II, character, Lev]
Generated description
Lev is a young, brave former Seraphite who becomes a key companion to Abby in The Last of Us Part II, known for his resilience, archery skills, and struggle against his sect’s rigid beliefs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lev
Target entity description: Lev is a young, brave former Seraphite who becomes a key companion to Abby in The Last of Us Part II, known for his resilience, archery skills, and struggle against his sect’s rigid beliefs.
  • A. Lev
    Lev is the Russian given name of the renowned writer Leo Tolstoy, under which he was known in his native language.
  • B. Leonid
    Leonid is a masculine given name of Slavic origin, notably borne by Soviet leader Leonid Brezhnev.
  • C. Levin
    Levin is a surname of Jewish origin borne by various notable individuals across fields such as business, politics, and the arts.
  • D. Levin
    Levin is a masculine given name of Germanic origin, historically borne by figures such as the Russian general Levin August von Bennigsen.
  • E. Levin
    Levin is a town in New Zealand’s North Island known as a service and retail hub for the surrounding agricultural Horowhenua district.
  • F. None of above. chosen

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_69ca84ca73208190957a900c8543bdcc completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d0422e88190a234ba74eb0dad25 completed April 1, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19118874c81909a97f874b1dc2db8 completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d193a5cdac8190b84564f397d00124 completed April 4, 2026, 10:41 p.m.
NED2 Entity disambiguation (via description) batch_69d19457c6488190a7bc72e1a27c088a completed April 4, 2026, 10:44 p.m.
Created at: March 30, 2026, 8:17 p.m.