Triple

T16075622
Position Surface form Disambiguated ID Type / Status
Subject Horemheb E389972 entity
Predicate spouse P13 FINISHED
Object Amenia
Amenia was an ancient Egyptian noblewoman known primarily as the wife of Pharaoh Horemheb during the late 18th Dynasty.
 E1192309 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: Amenia | Statement: [Horemheb, spouse, Amenia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Amenia
Context triple: [Horemheb, spouse, Amenia]
  • A. Amenia
    Amenia is a small rural town in eastern Dutchess County, New York, known for its scenic Hudson Valley landscapes and historic character.
  • B. Amurri
    Amurri is an Italian surname most notably associated with actress and lifestyle blogger Eva Amurri and her family.
  • C. Balya
    Balya is a small town and district in western Turkey known historically for its mining activities and rural character.
  • D. Mekeyir
    Mekeyir is an alternative name for the Shabo language, a little-documented and endangered language spoken in southwestern Ethiopia.
  • E. Erezée
    Erezée is a small rural municipality in the Ardennes region of southern Belgium, known for its scenic landscapes and quiet village character.
  • 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: Amenia
Triple: [Horemheb, spouse, Amenia]
Generated description
Amenia was an ancient Egyptian noblewoman known primarily as the wife of Pharaoh Horemheb during the late 18th Dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Amenia
Target entity description: Amenia was an ancient Egyptian noblewoman known primarily as the wife of Pharaoh Horemheb during the late 18th Dynasty.
  • A. Amenia
    Amenia is a small rural town in eastern Dutchess County, New York, known for its scenic Hudson Valley landscapes and historic character.
  • B. Amurri
    Amurri is an Italian surname most notably associated with actress and lifestyle blogger Eva Amurri and her family.
  • C. Balya
    Balya is a small town and district in western Turkey known historically for its mining activities and rural character.
  • D. Mekeyir
    Mekeyir is an alternative name for the Shabo language, a little-documented and endangered language spoken in southwestern Ethiopia.
  • E. Erezée
    Erezée is a small rural municipality in the Ardennes region of southern Belgium, known for its scenic landscapes and quiet village character.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183c27aac81909c56d200c0c51a0c completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe48715e48190a493d1e373dc7c5f completed May 10, 2026, 1:51 a.m.
NEDg Description generation batch_69ffe5407d408190b6c5ac22f2e62026 completed May 10, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_69ffe5d294c88190b60b9654899b5149 completed May 10, 2026, 1:56 a.m.
Created at: April 10, 2026, 4:57 a.m.