Triple
T5178351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hannah Peace |
E116855
|
entity |
| Predicate | hasMother |
P1909
|
FINISHED |
| Object | Eva Peace |
E115373
|
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: Eva Peace | Statement: [Hannah Peace, hasMother, Eva Peace]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eva Peace Context triple: [Hannah Peace, hasMother, Eva Peace]
-
A.
Eva Peace
chosen
Eva Peace is a fiercely independent, sharp-tongued matriarch in Toni Morrison’s novel "Sula," known for her unconventional life, physical disability, and complex relationship with her children and community.
-
B.
Eva Rice
Eva Rice is a British author and singer-songwriter, best known for her novel "The Lost Art of Keeping Secrets."
-
C.
Eva
Eva is a feminine given name of Hebrew origin, equivalent to "Eve" and widely used in many languages and cultures.
-
D.
Eva Orner
Eva Orner is an Australian documentary filmmaker and producer known for her hard-hitting political and human rights films, including the Academy Award-winning "Taxi to the Dark Side."
-
E.
Evelyn Baran
Evelyn Baran is best known as the wife of pioneering engineer Paul Baran, a key figure in the development of packet-switched networks and the internet.
- 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7976339481909ece900de22064f2 |
completed | March 20, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed95185ac819085fb42a69e014ec5 |
completed | March 21, 2026, 5:45 p.m. |
Created at: March 20, 2026, 1:45 p.m.