Triple

T13396001
Position Surface form Disambiguated ID Type / Status
Subject Lythraceae E319702 entity
Predicate includesGenus P1393 FINISHED
Object Heimia
Heimia is a small genus of flowering shrubs in the loosestrife family, known for its yellow blooms and traditional medicinal and psychoactive uses in the Americas.
 E1039631 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: Heimia | Statement: [Lythraceae, includesGenus, Heimia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heimia
Context triple: [Lythraceae, includesGenus, Heimia]
  • A. Hemma
    Hemma was a 9th-century Frankish noblewoman of the Carolingian dynasty, best known as the mother of Emperor Charles the Fat.
  • B. Haimos
    Haimos is a figure from Greek mythology known primarily as a sibling of Ida.
  • C. Doma
    Doma is a local government area and town in Nasarawa State, central Nigeria, known for its agrarian communities and proximity to the state capital, Lafia.
  • D. Meimad
    Meimad is a small Israeli religious Zionist political party known for its moderate, dovish positions and support for peace-oriented policies.
  • E. Kingaama
    Kingaama is a Bantu language belonging to the Sabaki branch, spoken along the East African coast.
  • 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: Heimia
Triple: [Lythraceae, includesGenus, Heimia]
Generated description
Heimia is a small genus of flowering shrubs in the loosestrife family, known for its yellow blooms and traditional medicinal and psychoactive uses in the Americas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heimia
Target entity description: Heimia is a small genus of flowering shrubs in the loosestrife family, known for its yellow blooms and traditional medicinal and psychoactive uses in the Americas.
  • A. Hemma
    Hemma was a 9th-century Frankish noblewoman of the Carolingian dynasty, best known as the mother of Emperor Charles the Fat.
  • B. Haimos
    Haimos is a figure from Greek mythology known primarily as a sibling of Ida.
  • C. Doma
    Doma is a local government area and town in Nasarawa State, central Nigeria, known for its agrarian communities and proximity to the state capital, Lafia.
  • D. Meimad
    Meimad is a small Israeli religious Zionist political party known for its moderate, dovish positions and support for peace-oriented policies.
  • E. Kingaama
    Kingaama is a Bantu language belonging to the Sabaki branch, spoken along the East African coast.
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dba0d892d08190b1b192b93fe3d72d completed April 12, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73071c0b88190bca3b15ea11c7491 completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f731c912708190af0249952e8824fb completed May 3, 2026, 11:30 a.m.
NED2 Entity disambiguation (via description) batch_69f732c14f5c8190afd989200d250783 completed May 3, 2026, 11:34 a.m.
Created at: April 9, 2026, 9:34 p.m.