Triple

T8126596
Position Surface form Disambiguated ID Type / Status
Subject Juan E189744 entity
Predicate hasEarlierForm P60231 FINISHED
Object Johannes E30173 NE FINISHED

How this triple was built (3 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: Johannes | Statement: [Juan, hasEarlierForm, Johannes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johannes
Context triple: [Juan, hasEarlierForm, Johannes]
  • A. Johannes chosen
    Johannes is the given first name of Paul Kruger, the prominent 19th-century Boer leader and president of the South African Republic.
  • B. Johannes
    Johannes is the given first name of the German nuclear physicist Hans D. Jensen, a Nobel Prize laureate in Physics.
  • C. Johannes
    Johannes is the given first name of Hubertus van Mook, a Dutch colonial administrator who served as Governor-General of the Dutch East Indies during and after World War II.
  • D. Johannes
    Johannes is a masculine given name of Hebrew origin, related to names like John and Johan and common in various European languages.
  • E. Johannes
    Johannes is the given name of Frederik Johannes Willem Reitz, a prominent South African lawyer, politician, and former State President of the Orange Free State.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasEarlierForm
Context triple: [Juan, hasEarlierForm, Johannes]
  • A. hasEarlierVersion chosen
    Indicates that one entity is an earlier or prior version of another entity in a version sequence.
  • B. hasEarlierPhase
    Indicates that one phase occurs before another phase in a process or sequence.
  • C. hasFormerCode
    Indicates that an entity was previously identified or referenced by an earlier code that is no longer current.
  • D. hasLaterPublicationForm
    Indicates that one publication exists in a later, revised, or otherwise subsequent form relative to another publication.
  • E. hasUseOfFormerBase
    Indicates that an entity currently utilizes, occupies, or benefits from a location or facility that previously served as a base for another party or purpose.
  • F. None of above.

Provenance (4 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_69ca82bb74848190afb1f18640632c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4c4c2e388190b86854f8b1765e61 completed March 31, 2026, 4:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc946b44d08190a042932ee908dc2f completed April 1, 2026, 3:43 a.m.
PD Predicate disambiguation batch_69cb3696379c8190a20965e59ed8f370 completed March 31, 2026, 2:51 a.m.
Created at: March 30, 2026, 5:34 p.m.