Triple

T18016550
Position Surface form Disambiguated ID Type / Status
Subject RetinaNet E431010 entity
Predicate hasAuthor P4244 FINISHED
Object Piotr Dollár NE NERFINISHED

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: Piotr Dollár | Statement: [RetinaNet, hasAuthor, Piotr Dollár]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Piotr Dollár
Context triple: [RetinaNet, hasAuthor, Piotr Dollár]
  • A. Piotr Dollár chosen
    Piotr Dollár is a computer vision researcher known for influential work on object detection, recognition, and deep learning methods at Microsoft and Meta (Facebook) AI Research.
  • B. Piotr Wojciechowski
    Piotr Wojciechowski is a Polish entrepreneur best known as a co-founder and leader of WB Electronics, a major defense and electronics company in Poland.
  • C. Piotr Wolski
    Piotr Wolski is a researcher known for co-authoring scientific work with machine learning scientist Marcin Andrychowicz.
  • D. Piotr Wysocki
    Piotr Wysocki was a Polish army officer and independence activist best known for initiating the November Uprising of 1830 against Russian rule.
  • E. Bogdan Pietruszka
    Bogdan Pietruszka is a Polish architect best known for co-designing the Monument to the Fallen Shipyard Workers of 1970 in Gdańsk, commemorating victims of the communist regime.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b9be5d0c819097e006f32d98753a completed April 19, 2026, 11:17 a.m.
Created at: April 10, 2026, 10:24 a.m.