Triple

T9784047
Position Surface form Disambiguated ID Type / Status
Subject Victorio E237446 entity
Predicate hasRelative P367 FINISHED
Object Lozen
Lozen was a renowned Chiricahua Apache warrior and prophetess known for her tactical skill and spiritual guidance during the Apache resistance to U.S. and Mexican forces in the late 19th century.
 E822065 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: Lozen | Statement: [Victorio, hasRelative, Lozen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lozen
Context triple: [Victorio, hasRelative, Lozen]
  • A. Looz
    Looz is the historical name of the medieval County of Loon, a former principality in what is now eastern Belgium.
  • B. Loëx
    Loëx is a small locality within the municipality of Bernex in the canton of Geneva, Switzerland.
  • C. Zayton
    Zayton is the historical name used by medieval Arab and European traders for the major Chinese port city of Quanzhou, once one of the world’s busiest maritime trade centers.
  • D. Melinta
    Melinta is a small coastal village on the Greek island of Lesbos, known for its quiet beaches and traditional Aegean character.
  • E. Lodoselo
    Lodoselo is a small village in the municipality of Sarreaus, in the province of Ourense, Galicia, Spain.
  • 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: Lozen
Triple: [Victorio, hasRelative, Lozen]
Generated description
Lozen was a renowned Chiricahua Apache warrior and prophetess known for her tactical skill and spiritual guidance during the Apache resistance to U.S. and Mexican forces in the late 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lozen
Target entity description: Lozen was a renowned Chiricahua Apache warrior and prophetess known for her tactical skill and spiritual guidance during the Apache resistance to U.S. and Mexican forces in the late 19th century.
  • A. Looz
    Looz is the historical name of the medieval County of Loon, a former principality in what is now eastern Belgium.
  • B. Loëx
    Loëx is a small locality within the municipality of Bernex in the canton of Geneva, Switzerland.
  • C. Zayton
    Zayton is the historical name used by medieval Arab and European traders for the major Chinese port city of Quanzhou, once one of the world’s busiest maritime trade centers.
  • D. Melinta
    Melinta is a small coastal village on the Greek island of Lesbos, known for its quiet beaches and traditional Aegean character.
  • E. Lodoselo
    Lodoselo is a small village in the municipality of Sarreaus, in the province of Ourense, Galicia, Spain.
  • 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_69ca84da927881909bda80caecad6010 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda1b7740c8190bfb4997eb683d78a completed April 1, 2026, 10:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c41fc5508190a759cdda8416673a completed April 5, 2026, 2:08 a.m.
NEDg Description generation batch_69d1c53b888081908ecb01884f064b80 completed April 5, 2026, 2:13 a.m.
NED2 Entity disambiguation (via description) batch_69d1c5a1cfb08190b6c16e5309dbf2b8 completed April 5, 2026, 2:14 a.m.
Created at: March 30, 2026, 8:27 p.m.