Triple

T5782921
Position Surface form Disambiguated ID Type / Status
Subject Toby E128202 entity
Predicate hasVariantSpelling P457 FINISHED
Object Tobi
Tobi is a given name, often used as a variant of Toby, that can be used for people of any gender in various cultures.
E543518 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: Tobi | Statement: [Toby, hasVariantSpelling, Tobi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tobi
Context triple: [Toby, hasVariantSpelling, Tobi]
  • A. Tio
    Tio is a coastal town in Eritrea’s Southern Red Sea Region, known historically as a small port on the Red Sea.
  • B. Nagato
    Nagato was a famous Japanese battleship of the Imperial Japanese Navy, notable for serving as Admiral Yamamoto’s flagship during the attack on Pearl Harbor and later participating in major World War II engagements.
  • C. Obi
    Obi is a local government area and town in Benue State, Nigeria, traditionally associated with and inhabited by the Idoma people.
  • D. Obi
    Obi is a local government area in Nasarawa State, Nigeria, serving as an administrative subdivision of the state.
  • E. Toby
    Toby is a central protagonist in Margaret Atwood’s dystopian MaddAddam trilogy, known for her resilience, survival skills, and complex moral perspective in a post-apocalyptic world.
  • 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: Tobi
Triple: [Toby, hasVariantSpelling, Tobi]
Generated description
Tobi is a given name, often used as a variant of Toby, that can be used for people of any gender in various cultures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tobi
Target entity description: Tobi is a given name, often used as a variant of Toby, that can be used for people of any gender in various cultures.
  • A. Tio
    Tio is a coastal town in Eritrea’s Southern Red Sea Region, known historically as a small port on the Red Sea.
  • B. Nagato
    Nagato was a famous Japanese battleship of the Imperial Japanese Navy, notable for serving as Admiral Yamamoto’s flagship during the attack on Pearl Harbor and later participating in major World War II engagements.
  • C. Obi
    Obi is a local government area and town in Benue State, Nigeria, traditionally associated with and inhabited by the Idoma people.
  • D. Obi
    Obi is a local government area in Nasarawa State, Nigeria, serving as an administrative subdivision of the state.
  • E. Toby
    Toby is one of the central sailor protagonists in Herman Melville’s semi-autobiographical novel "Typee," known for his role in the narrative of escape and survival among a Polynesian tribe.
  • 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_69c0084450048190bc647b649a05136b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02a184870819084251554eae1e33c completed March 22, 2026, 5:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e7a1cb88190980e0cf675aaa906 completed March 22, 2026, 11:42 p.m.
NEDg Description generation batch_69c086b2f5888190a986efaf948b25fb completed March 23, 2026, 12:17 a.m.
NED2 Entity disambiguation (via description) batch_69c087493f808190bec82872e44af85c completed March 23, 2026, 12:20 a.m.
Created at: March 22, 2026, 3:50 p.m.