Triple
T16146243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Ludwig |
E391789
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Molly Pitcher |
E1135771
|
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: Molly Pitcher | Statement: [Mary Ludwig, nickname, Molly Pitcher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Molly Pitcher Context triple: [Mary Ludwig, nickname, Molly Pitcher]
-
A.
Molly Pitcher
chosen
Molly Pitcher is a legendary figure of the American Revolutionary War, often identified with Mary Ludwig Hays, celebrated for carrying water to soldiers and manning a cannon at the Battle of Monmouth.
-
B.
Margaret Sergeant
Margaret Sergeant is known primarily as the daughter of British journalist and political commentator John Sergeant.
-
C.
Sarah Sergeant
Sarah Sergeant is known as the daughter of British journalist and broadcaster John Sergeant.
-
D.
Sarah Sergeant
Sarah Sergeant was the wife of 19th-century American politician and Virginia governor Henry A. Wise.
-
E.
Mary Dickson
Mary Dickson is known as the wife of American film director Richard Fleischer.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d9376fc8190bd9ef586b00c1d3b |
completed | April 17, 2026, 11:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fffef2f49081909841a1f9bfbd622b |
completed | May 10, 2026, 3:43 a.m. |
Created at: April 10, 2026, 5:01 a.m.