Triple

T13766936
Position Surface form Disambiguated ID Type / Status
Subject Carl Humann E330773 entity
Predicate familyName P18 FINISHED
Object Humann
Humann is a German surname most notably associated with archaeologist Carl Humann, who led the excavation of the Pergamon Altar.
 E1058639 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: Humann | Statement: [Carl Humann, familyName, Humann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Humann
Context triple: [Carl Humann, familyName, Humann]
  • A. el Humano
    El Humano is the sobriquet of King Martin I of Aragon, highlighting his reputation for justice and humane character during his late 14th- and early 15th-century reign.
  • B. Humanes
    Humanes is a municipality in central Spain that serves as a stop on the C-5 commuter rail line connecting it with Madrid and other nearby towns.
  • C. "Human"
    "Human" is a pop song written by Shelly Peiken, best known for being recorded and popularized by Christina Perri.
  • D. Manav
    Manav is the central protagonist of the 1999 Hindi musical romance film "Taal," portrayed by actor Akshaye Khanna.
  • E. Humash
    Humash is the Hebrew term for the Five Books of Moses, the foundational text of the Jewish Torah.
  • 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: Humann
Triple: [Carl Humann, familyName, Humann]
Generated description
Humann is a German surname most notably associated with archaeologist Carl Humann, who led the excavation of the Pergamon Altar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Humann
Target entity description: Humann is a German surname most notably associated with archaeologist Carl Humann, who led the excavation of the Pergamon Altar.
  • A. el Humano
    El Humano is the sobriquet of King Martin I of Aragon, highlighting his reputation for justice and humane character during his late 14th- and early 15th-century reign.
  • B. Humanes
    Humanes is a municipality in central Spain that serves as a stop on the C-5 commuter rail line connecting it with Madrid and other nearby towns.
  • C. "Human"
    "Human" is a pop song written by Shelly Peiken, best known for being recorded and popularized by Christina Perri.
  • D. Manav
    Manav is the central protagonist of the 1999 Hindi musical romance film "Taal," portrayed by actor Akshaye Khanna.
  • E. Humash
    Humash is the Hebrew term for the Five Books of Moses, the foundational text of the Jewish Torah.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0227f2c48190983ccc9395e4e7a2 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a864c0ac81909e5fcd134ea66414 completed May 3, 2026, 7:56 p.m.
NEDg Description generation batch_69f7a94390988190bcaedcda0b691fbb completed May 3, 2026, 8 p.m.
NED2 Entity disambiguation (via description) batch_69f7a9fe250c8190b66062e7fcea8d86 completed May 3, 2026, 8:03 p.m.
Created at: April 9, 2026, 10:10 p.m.