Triple
T721520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michelangelo |
E14626
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | David |
E34716
|
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: David | Statement: [Michelangelo, notableWork, David]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Context triple: [Michelangelo, notableWork, David]
-
A.
David
David is the middle name of Dwight D. Eisenhower, the 34th president of the United States and Supreme Allied Commander in Europe during World War II.
-
B.
David
David is a major city in western Panama and the capital of Chiriquí Province.
-
C.
David
chosen
David is a common given name and surname of Hebrew origin, widely used across many cultures and historically associated with the biblical King David.
-
D.
Arthur
Arthur is a long-running animated children's television series that follows the everyday adventures and life lessons of Arthur Read, an anthropomorphic aardvark, and his friends and family.
-
E.
Arthur
Arthur is the given name of the renowned American playwright Arthur Miller, known for works such as "Death of a Salesman" and "The Crucible."
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a58fa41c819082de2cc4e0cb2943 |
completed | March 1, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acbf00f0e08190b90a719952216204 |
completed | March 8, 2026, 12:12 a.m. |
Created at: March 1, 2026, 7:37 p.m.