Triple
T20298071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cracker |
E505404
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Geraldine Somerville |
—
|
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: Geraldine Somerville | Statement: [Cracker, starring, Geraldine Somerville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geraldine Somerville Context triple: [Cracker, starring, Geraldine Somerville]
-
A.
Geraldine Somerville
chosen
Geraldine Somerville is an Irish-born British actress best known for her roles in the Harry Potter film series and numerous acclaimed British television dramas and period films.
-
B.
Margaret Spruance
Margaret Spruance was the daughter of U.S. Navy Admiral Raymond A. Spruance, a prominent World War II Pacific Fleet commander.
-
C.
Claudia Cowan
Claudia Cowan is an American television news reporter best known for her work as a correspondent for Fox News Channel.
-
D.
Cathleen Neilson
Cathleen Neilson was an American socialite known for her marriage into the wealthy Vanderbilt family through Reginald Claypoole Vanderbilt.
-
E.
Rosemary Telesco
Rosemary Telesco is the young girl who becomes the object of the protagonist's first crush in the romantic comedy film "Little Manhattan."
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6770a2cec8190912d6b0dbabc78bc |
completed | April 20, 2026, 6:57 p.m. |
Created at: April 16, 2026, 11:16 a.m.