Triple

T74801
Position Surface form Disambiguated ID Type / Status
Subject Erwin Rommel E1496 entity
Predicate givenName P17 FINISHED
Object Erwin
Erwin is a masculine given name of German origin, historically associated with figures such as the World War II field marshal Erwin Rommel.
 E20767 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: Erwin | Statement: [Erwin Rommel, givenName, Erwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Erwin
Context triple: [Erwin Rommel, givenName, Erwin]
  • A. Theodor
    Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
  • B. Edwin
    Edwin is a masculine given name of Old English origin meaning "rich friend" or "prosperous friend."
  • C. Otto
    Otto is the title of one of the early nominative reports that were later incorporated into the official United States Reports, documenting decisions of the U.S. Supreme Court.
  • D. Andreas
    Andreas is a masculine given name of Greek origin, commonly used in various European and international cultures.
  • E. Johan
    Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
  • 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: Erwin
Triple: [Erwin Rommel, givenName, Erwin]
Generated description
Erwin is a masculine given name of German origin, historically associated with figures such as the World War II field marshal Erwin Rommel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Erwin
Target entity description: Erwin is a masculine given name of German origin, historically associated with figures such as the World War II field marshal Erwin Rommel.
  • A. Theodor
    Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
  • B. Edwin
    Edwin is a masculine given name of Old English origin meaning "rich friend" or "prosperous friend."
  • C. Otto
    Otto is the title of one of the early nominative reports that were later incorporated into the official United States Reports, documenting decisions of the U.S. Supreme Court.
  • D. Andreas
    Andreas is a masculine given name of Greek origin, commonly used in various European and international cultures.
  • E. Johan
    Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
  • 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_69a24c60d19c8190a1b6c105ca59ef5b completed Feb. 28, 2026, 2:01 a.m.
NER Named-entity recognition batch_69a24f1b99a48190aec004ecd49b4a0d completed Feb. 28, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2e0f3430481908a6304e5938c2eac completed Feb. 28, 2026, 12:34 p.m.
NEDg Description generation batch_69a2e1b356948190a278cd62d59432cb completed Feb. 28, 2026, 12:38 p.m.
NED2 Entity disambiguation (via description) batch_69a2e231b0048190823f9b6cd768de3c completed Feb. 28, 2026, 12:40 p.m.
Created at: Feb. 28, 2026, 2:06 a.m.