Triple
T15111170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harkness |
E360913
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Deborah Harkness |
E1092793
|
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: Deborah Harkness | Statement: [Harkness, hasNotableBearer, Deborah Harkness]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deborah Harkness Context triple: [Harkness, hasNotableBearer, Deborah Harkness]
-
A.
Deborah Harkness
chosen
Deborah Harkness is an American historian and novelist best known for her bestselling All Souls Trilogy, which blends fantasy, history, and romance.
-
B.
Susanna Bennett
Susanna Bennett was the wife of Irish Gothic writer Sheridan Le Fanu, known primarily through her marriage to the influential Victorian author.
-
C.
Naomi Novik
Naomi Novik is an American fantasy author best known for her Temeraire series and the award-winning novels Uprooted and Spinning Silver.
-
D.
Mary K. Vernon
Mary K. Vernon is a computer scientist known for her research in computer systems performance and for mentoring prominent scholars in the field.
-
E.
Jacquetta Hawkes
Jacquetta Hawkes was a British archaeologist and writer known for her influential books on prehistory and for popularizing archaeology in the mid-20th century.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0058c04f481909deeac0271d961b6 |
completed | April 15, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feb7eb139c8190b76393e4a8be576b |
completed | May 9, 2026, 4:28 a.m. |
Created at: April 10, 2026, 3:05 a.m.