Triple
T22383770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carl Djerassi |
E553340
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Djerassi |
—
|
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: Djerassi | Statement: [Carl Djerassi, familyName, Djerassi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Djerassi Context triple: [Carl Djerassi, familyName, Djerassi]
-
A.
Djerassi
chosen
Djerassi is a surname most prominently associated with Carl Djerassi, the chemist known as a co-inventor of the oral contraceptive pill.
-
B.
Scheinberg
Scheinberg is a mountain peak in the Steigerwald range of Germany, known as its highest point.
-
C.
Redon
Redon is a deity from ancient Illyrian pagan religion, likely associated with local cult worship in the western Balkans.
-
D.
Redon
Redon is a French surname most notably associated with the Symbolist painter and printmaker Odilon Redon.
-
E.
Redon
Redon is a small historic town in western France known for its canal junction and medieval abbey, situated near the borders of Brittany and Pays de la Loire.
- 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_69e11e4cf87c8190a1ff474daec326b7 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1582d8e548190a7330de49d519675 |
completed | April 29, 2026, 1 a.m. |
Created at: April 16, 2026, 8:45 p.m.