Triple
T15562020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcel Bloch |
E371021
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Serge Dassault |
E724021
|
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: Serge Dassault | Statement: [Marcel Bloch, child, Serge Dassault]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Serge Dassault Context triple: [Marcel Bloch, child, Serge Dassault]
-
A.
Serge Dassault
chosen
Serge Dassault was a French industrialist, politician, and billionaire who led the Dassault aviation and media empire.
-
B.
Marcel Dassault
Marcel Dassault was a prominent French aircraft industrialist, engineer, and politician who founded the Dassault aviation empire.
-
C.
François Delarozière
François Delarozière is a French artist and designer renowned for his monumental mechanical sculptures and fantastical urban installations.
-
D.
Jean Galland
Jean Galland was a French film and stage actor active in the early to mid-20th century.
-
E.
François Hanriot
François Hanriot was a radical French revolutionary leader and commander of the National Guard in Paris during the Reign of Terror.
- 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_69d85cc6cf40819091f4a5facee1ebe6 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ddb4c0c81909b3f4c75c91f7f3f |
completed | April 16, 2026, 2:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f2f229081908faf15f9d8efecbf |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:09 a.m.