Triple
T20119215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weather Underground |
E490552
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Bernardine Dohrn |
—
|
NE NERFINISHED |
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: Bernardine Dohrn | Statement: [Weather Underground, notableMember, Bernardine Dohrn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bernardine Dohrn Context triple: [Weather Underground, notableMember, Bernardine Dohrn]
-
A.
Bernardine Dohrn
chosen
Bernardine Dohrn is an American former radical activist, best known as a leader of the Weather Underground and a prominent figure in the 1960s–70s New Left movement.
-
B.
Margaret Dusa
Margaret Dusa is the given first name of the prominent British-American mathematician Dusa McDuff, known for her influential work in symplectic geometry.
-
C.
Dorothy Neumann
Dorothy Neumann was an American character actress known for her numerous supporting roles in mid-20th-century films and television.
-
D.
Dorothy M. Donahoe
Dorothy M. Donahoe was a California legislator and education advocate best known for her pivotal role in shaping state higher education policy.
-
E.
Margaret Rudman
Margaret Rudman is known as the wife of the late U.S. Senator Warren Rudman of New Hampshire.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673c32bc8190a52875961fbcc5e2 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.