Triple
T22956917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawthorne |
E570784
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Hannah Hodson |
—
|
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: Hannah Hodson | Statement: [Hawthorne, starring, Hannah Hodson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hannah Hodson Context triple: [Hawthorne, starring, Hannah Hodson]
-
A.
Hannah Hodson
chosen
Hannah Hodson is an American actress best known for her roles in film and television, including early recognition for her performance in the inspirational drama "The Ron Clark Story."
-
B.
Hannah Clements
Hannah Clements is known as the daughter of James P. Clements, the president of Clemson University.
-
C.
Hannah Higgins
Hannah Higgins is a central character in the romantic comedy film "The Makeover," portrayed as an ambitious, polished professional whose life changes when she undertakes a transformative personal and social experiment.
-
D.
Hannah Gill
Hannah Gill is a fictional character in "The Truman Show," an actress who plays Truman Burbank’s on-screen wife within the film’s constructed reality.
-
E.
Hannah Nicholls
Hannah Nicholls is known as the wife of British novelist and screenwriter David Nicholls.
- 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f15ebc8190bf477539f7c23985 |
completed | April 29, 2026, 3:58 a.m. |
Created at: April 17, 2026, 3:47 p.m.