Triple
T1637376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welcome to Marwen |
E35386
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Jeremiah O’Driscoll |
E219865
|
NE FINISHED |
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: Jeremiah O’Driscoll | Statement: [Welcome to Marwen, editedBy, Jeremiah O’Driscoll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeremiah O’Driscoll Context triple: [Welcome to Marwen, editedBy, Jeremiah O’Driscoll]
-
A.
Jeremiah O’Driscoll
chosen
Jeremiah O’Driscoll is a film editor best known for his work on major feature films, including serving as the editor of "The Polar Express."
-
B.
Andrew Duggan
Andrew Duggan was an American character actor known for his prolific work in film and television from the 1950s through the 1980s.
-
C.
James O’Donnell
James O’Donnell was a 19th-century Irish-American architect best known for designing Montreal’s iconic Notre-Dame Basilica in the Gothic Revival style.
-
D.
Declan Gaffney
Declan Gaffney is a music producer and engineer best known for his extensive work with U2 on several of their studio albums.
-
E.
Daniel Neeson
Daniel Neeson is the son of acclaimed Irish actor Liam Neeson and his late wife, actress Natasha Richardson.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a886036bc081909ff5de16dbe5e8ea |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90a192d588190bbfa4693ed787c05 |
completed | March 5, 2026, 4:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae26e9748081909532426be2f198d1 |
completed | March 9, 2026, 1:48 a.m. |
Created at: March 4, 2026, 7:28 p.m.