Triple
T2327336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Gates Wallace |
E48317
|
entity |
| Predicate | family name |
P18
|
FINISHED |
| Object | Wallace |
E33936
|
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: Wallace | Statement: [Margaret Gates Wallace, family name, Wallace]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wallace Context triple: [Margaret Gates Wallace, family name, Wallace]
-
A.
Wallace
Wallace is a volume series of early United States Supreme Court case reports compiled by reporter John William Wallace, later incorporated into the official United States Reports.
-
B.
Wallace
Wallace is a notable figure who succeeded Black in a position of leadership or prominence, likely within a political or organizational context.
-
C.
Wallace
Wallace is the maiden surname of Bess Truman, the wife of U.S. President Harry S. Truman and former First Lady of the United States.
-
D.
Wallace
chosen
Wallace is a common English and Scottish surname borne by numerous notable figures in politics, science, and the arts.
-
E.
Walter
Walter is a masculine given name of Germanic origin that has been widely used in English-speaking countries.
- 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc64c7f1881909b0d847f7782e803 |
completed | March 7, 2026, 6:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae897243c48190a18b0e02ad664ead |
completed | March 9, 2026, 8:48 a.m. |
Created at: March 4, 2026, 7:50 p.m.