Triple
T19040678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pingree |
E465991
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Hazel Pingree |
—
|
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: Hazel Pingree | Statement: [Pingree, hasNotableBearer, Hazel Pingree]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hazel Pingree Context triple: [Pingree, hasNotableBearer, Hazel Pingree]
-
A.
Hazel Pingree
chosen
Hazel Pingree is a historic American shoe brand known for its high-quality, durable footwear.
-
B.
Rochelle Pingree
Rochelle Pingree is an individual whose legal name is formally registered as "Rochelle Pingree."
-
C.
Hannah Pingree
Hannah Pingree is an American politician from Maine who has served as Speaker of the Maine House of Representatives and is the daughter of U.S. Representative Chellie Pingree.
-
D.
Marjorie Bransfield
Marjorie Bransfield is an American actress known for her film and television roles in the late 1980s and early 1990s.
-
E.
Linda Munn
Linda Munn is a New Zealand artist and activist best known as one of the designers of the Tino Rangatiratanga flag, a key symbol of Māori sovereignty and identity.
- 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d80054c88190a9d3a49aed504235 |
completed | April 20, 2026, 7:38 a.m. |
Created at: April 10, 2026, 12:02 p.m.