Triple
T23018091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terror by Night |
E573086
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Mary Forbes |
—
|
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: Mary Forbes | Statement: [Terror by Night, starring, Mary Forbes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Forbes Context triple: [Terror by Night, starring, Mary Forbes]
-
A.
Mary Forbes
chosen
Mary Forbes was a British-born character actress known for her numerous supporting roles in American films during the early to mid-20th century.
-
B.
Mary Forbes
Mary Forbes was a Scottish noblewoman of the Forbes family best known as the mother of George Gordon, 1st Earl of Aberdeen.
-
C.
Sarah Forbes
Sarah Forbes is the central protagonist of the science fiction television series "Odyssey 5," around whom much of the show's time-traveling narrative and emotional stakes revolve.
-
D.
Katherine Elizabeth Forbes
Katherine Elizabeth Forbes was the wife of British politician William Wellesley-Pole, connecting her to the prominent Wellesley family of the late 18th and early 19th centuries.
-
E.
Miss Forbes
Miss Forbes is the protagonist of the novel "Miss Forbes’s Summer of Happiness," around whom the story’s events and emotional journey revolve.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.