Triple
T21449225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heather Miller |
E529163
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Sawyer |
—
|
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: Sawyer | Statement: [Heather Miller, familyName, Sawyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sawyer Context triple: [Heather Miller, familyName, Sawyer]
-
A.
Sawyer
chosen
Sawyer is a surname of English origin commonly borne by individuals in English-speaking countries.
-
B.
Sawyer
Sawyer is a collaborative industrial robot arm developed by Rethink Robotics for flexible, safe automation tasks alongside human workers.
-
C.
Alex Sawyer
Alex Sawyer is a British political aide and former Conservative Party councillor, best known as the husband of UK politician Priti Patel.
-
D.
Swoyer
Swoyer is a surname associated with individuals such as Nancy Walker.
-
E.
Parker Sawyers
Parker Sawyers is an American actor best known for portraying a young Barack Obama in the film "Southside with You" and for his work in various international film and television productions.
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9d11ca48190aafe25c97dfa5578 |
completed | April 23, 2026, 9:43 a.m. |
Created at: April 16, 2026, 6:06 p.m.