Triple
T7213707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Hardy |
E149473
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hardy |
E120385
|
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: Hardy | Statement: [Andy Hardy, familyName, Hardy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hardy Context triple: [Andy Hardy, familyName, Hardy]
-
A.
Hardy
chosen
Hardy is a surname most famously associated with the English mathematician G. H. Hardy, known for his contributions to number theory and mathematical analysis.
-
B.
Hardy
Hardy is a classification used in Scottish mountaineering to denote certain notable peaks recognized by climbers and hillwalkers.
-
C.
Louis Thomas Hardy
Louis Thomas Hardy is the eldest son of English actor Tom Hardy.
-
D.
Dudley Hardy
Dudley Hardy was a British painter and illustrator best known for his influential late 19th-century poster art and contributions to the development of modern graphic design.
-
E.
J. F. Hardy
J. F. Hardy was a mountaineer known for participating in the first recorded ascent of the Alpine peak Liskamm.
- 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_69c687eca814819095abb52316b1af80 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e98cbebc8190941e76259c988790 |
completed | March 27, 2026, 8:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7bfd41a8881909dc94c01f6601b2e |
completed | March 28, 2026, 11:47 a.m. |
Created at: March 27, 2026, 2:53 p.m.