Triple
T8453091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frederick Soddy |
E199847
|
entity |
| Predicate | NobelPrizeCategory |
P1861
|
FINISHED |
| Object | Chemistry |
E73795
|
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: Chemistry | Statement: [Frederick Soddy, NobelPrizeCategory, Chemistry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chemistry Context triple: [Frederick Soddy, NobelPrizeCategory, Chemistry]
-
A.
Chemistry
chosen
Chemistry is the branch of science that studies the composition, structure, properties, and transformations of matter at the atomic and molecular levels.
-
B.
Chimica
Chimica is a specialized scientific database focused on chemistry literature and research.
-
C.
CHM
CHM is the National Rail station code for Chelmsford railway station in Essex, England.
-
D.
Chemical Science
Chemical Science is a leading peer-reviewed open-access journal covering cutting-edge research across all areas of chemistry, published by the Royal Society of Chemistry.
-
E.
General Chemistry
General Chemistry is a foundational chemistry textbook by Linus Pauling that helped shape modern chemical education through its clear exposition of atomic structure, bonding, and chemical principles.
- 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_69ca8318231881908fd1bc1c4d45d286 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe48aee388190864ef1186d5ee419 |
completed | March 31, 2026, 3:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1dda289c81908e0cc8e1a504caa1 |
completed | April 2, 2026, 7:42 a.m. |
Created at: March 30, 2026, 6:09 p.m.