Triple
T15519810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | du Puy |
E368930
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | duPuy |
E368930
|
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: duPuy | Statement: [du Puy, hasVariant, duPuy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: duPuy Context triple: [du Puy, hasVariant, duPuy]
-
A.
du Puy
chosen
du Puy is a French-origin surname historically associated with figures such as Maud du Puy, wife of the 12th-century English noble William Marshal.
-
B.
Dupuy
Dupuy is a French surname borne by various notable figures in politics, arts, and sciences.
-
C.
Duch
Duch is a Polish surname most notably borne by Bronisław Duch, a general in the Polish Army during World War II.
-
D.
Dupeyron
Dupeyron is a French surname most notably associated with film director and screenwriter François Dupeyron.
-
E.
DUHAC
DUHAC is the athletics and running club of Trinity College Dublin, catering to students and staff across a range of track, field, and distance events.
- 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_69d85a1794cc8190b0b428716296e63e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e040343d9c8190a7d1f197c108bd9d |
completed | April 16, 2026, 1:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff3d52cf1c8190b18bff0b925355a3 |
completed | May 9, 2026, 1:57 p.m. |
Created at: April 10, 2026, 4:04 a.m.