Triple

T37744095
Position Surface form Disambiguated ID Type / Status
Subject War of the Axe E940798 entity
Predicate commandedBy P1407 FINISHED
Object Andries Stockenström
Andries Stockenström was a 19th-century South African soldier and colonial administrator known for his role in the Cape Frontier Wars and his efforts to reform frontier policy toward the Xhosa.
E2285016 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: Andries Stockenström | Statement: [War of the Axe, commandedBy, Andries Stockenström]
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: Andries Stockenström
Triple: [War of the Axe, commandedBy, Andries Stockenström]
Generated description
Andries Stockenström was a 19th-century South African soldier and colonial administrator known for his role in the Cape Frontier Wars and his efforts to reform frontier policy toward the Xhosa.

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_69f76ee0e32c8190b40a3b4cf590337c completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fbaec146a4819096a7cf40618a95e4 completed May 6, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a44b3916758819092544ab28c7b5afa completed July 1, 2026, 6:28 a.m.
NEDg Description generation batch_6a44b587c3ec8190997b70be1d8c7c15 completed July 1, 2026, 6:36 a.m.
NED2 Entity disambiguation (via description) batch_6a44b5e52690819086e95e560158612c completed July 1, 2026, 6:38 a.m.
Created at: May 3, 2026, 4:19 p.m.