Triple
T10334230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyacinth |
E242957
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Hyacinthe |
E856612
|
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: Hyacinthe | Statement: [Hyacinth, hasVariant, Hyacinthe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hyacinthe Context triple: [Hyacinth, hasVariant, Hyacinthe]
-
A.
Jacinthe
chosen
Jacinthe is a variant form of the name Hyacinth, often associated with the fragrant spring flower and its rich, jewel-like colors.
-
B.
Delphine
Delphine is an epistolary novel by Madame de Staël that explores themes of love, social convention, and women's independence in late 18th-century French society.
-
C.
Tiphaine
Tiphaine is a French given name, notably borne by Tiphaine Auzière, the daughter of Brigitte Macron.
-
D.
Philomé
Philomé is the given name of Philomé Obin, a prominent Haitian painter known for his detailed depictions of historical and everyday life scenes.
-
E.
Hélécine
Hélécine is a small rural municipality in the province of Walloon Brabant in Wallonia, Belgium.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4dfc366b481909c49f199892e9d42 |
completed | April 7, 2026, 10:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d794fe4fe481908e4c343ceeb5de25 |
completed | April 9, 2026, 12:01 p.m. |
Created at: April 6, 2026, 11:53 a.m.