Triple
T3069754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean-Paul Sartre |
E63991
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Jean-Paul |
E112550
|
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: Jean-Paul | Statement: [Jean-Paul Sartre, givenName, Jean-Paul]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Paul Context triple: [Jean-Paul Sartre, givenName, Jean-Paul]
-
A.
Jean-Paul
chosen
Jean-Paul is a masculine French given name most famously borne by the revolutionary leader and journalist Jean-Paul Marat.
-
B.
Jean-Pierre
Jean-Pierre is a French given name commonly used as a masculine compound first name.
-
C.
Gustave Ador
Gustave Ador was a Swiss politician and statesman who served as President of the Swiss Confederation and was a leading figure in the International Committee of the Red Cross.
-
D.
Alain
Alain is a masculine given name of French origin, derived from the Breton name Alan and widely used in French-speaking countries.
-
E.
Jean-Paul Agon
Jean-Paul Agon is a French business executive best known for serving as the longtime CEO and later chairman of global cosmetics giant L'Oréal.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada100f0b8819095da366fdc6803a8 |
completed | March 8, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1f87f6a3881908ae313f62ff13159 |
completed | March 11, 2026, 11:19 p.m. |
Created at: March 8, 2026, 3:02 p.m.