Triple
T10962538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amalfi |
E259010
|
entity |
| Predicate | traditionalProduct |
P3553
|
FINISHED |
| Object | Amalfi lemons |
E808192
|
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: Amalfi lemons | Statement: [Amalfi, traditionalProduct, Amalfi lemons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amalfi lemons Context triple: [Amalfi, traditionalProduct, Amalfi lemons]
-
A.
Lemon
Lemon is a 1993 song by U2 from their album "Zooropa," noted for its dance-oriented sound and Bono’s distinctive falsetto vocals.
-
B.
Lemon
chosen
Lemon is a citrus fruit known for its bright yellow color, sour taste, and wide use in cooking, beverages, and cleaning.
-
C.
Zitrone
Zitrone is a French surname most notably borne by Léon Zitrone, a prominent 20th-century television journalist and presenter in France.
-
D.
Lemonum
Lemonum was an important ancient Roman town in Gaul, located at the site of modern-day Poitiers in western France.
-
E.
Malvazia
Malvazia is a traditional Mediterranean wine grape variety, best known for producing rich, aromatic Malvasia-style wines ranging from dry to lusciously sweet.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7714714c88190926ebd48b09150c6 |
completed | April 9, 2026, 9:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d761d3c48190af8e0aedf96ee99f |
completed | April 18, 2026, 12:59 a.m. |
Created at: April 8, 2026, 9:23 p.m.