Triple

T74809
Position Surface form Disambiguated ID Type / Status
Subject Erwin Rommel E1496 entity
Predicate militaryBranch P253 FINISHED
Object Heer E9485 NE FINISHED

How this triple was built (2 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: Heer | Statement: [Erwin Rommel, militaryBranch, Heer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heer
Context triple: [Erwin Rommel, militaryBranch, Heer]
  • A. Heer chosen
    The Heer was the land-based component of Nazi Germany’s armed forces, serving as its primary army during World War II.
  • B. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • C. Fida'i
    Fida'i is the national anthem of the State of Palestine, expressing Palestinian identity, struggle, and aspirations for freedom and self-determination.
  • D. Heeren XVII
    Heeren XVII was the central governing board of the Dutch East India Company, composed of seventeen powerful directors who oversaw its global trade and colonial activities.
  • E. Shuar
    Shuar is an indigenous language of the Jivaroan family spoken by the Shuar people primarily in the Amazonian regions of Ecuador and Peru.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a26c1b81a88190ba473b28dd88fdb8 completed Feb. 28, 2026, 4:16 a.m.
Created at: Feb. 28, 2026, 2:06 a.m.