Triple
T22067464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Henry Perkin |
E545312
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Perkin |
—
|
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: Perkin | Statement: [William Henry Perkin, familyName, Perkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perkin Context triple: [William Henry Perkin, familyName, Perkin]
-
A.
Perkin
chosen
Perkin is a surname most famously associated with William Henry Perkin, the English chemist who discovered the first synthetic dye, mauveine.
-
B.
Perkin & Sons
Perkin & Sons was the chemical manufacturing company established by William Henry Perkin to commercialize his pioneering synthetic dye discoveries, including the first aniline dye, mauveine.
-
C.
Beckman
Beckman is a German-origin surname borne by various notable individuals across fields such as science, business, and the arts.
-
D.
Ostwald
Ostwald is a German surname most notably associated with Nobel Prize–winning chemist Wilhelm Ostwald.
-
E.
Coumet
Coumet is a French surname most notably borne by Jérôme Coumet, a contemporary French politician.
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12884937c819095d3af69123fa2cb |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:27 p.m.