Triple
T3192390
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albert Finney |
E66852
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Pene Delmage
Pene Delmage is a British travel agent and the widow of acclaimed English actor Albert Finney.
|
E345155
|
NE FINISHED |
How this triple was built (4 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: Pene Delmage | Statement: [Albert Finney, spouse, Pene Delmage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pene Delmage Context triple: [Albert Finney, spouse, Pene Delmage]
-
A.
Lance LePere
Lance LePere is an American fashion designer and longtime creative collaborator best known as the husband of designer Michael Kors.
-
B.
Donnel Pumphrey
Donnel Pumphrey is an American former running back best known for his record-setting college career at San Diego State University, where he became the NCAA's all-time leading rusher.
-
C.
Alann Lopes
Alann Lopes is an entrepreneur and founder associated with the educational organization Sally Ride Science.
-
D.
Nick Clemons
Nick Clemons is an American musician and singer-songwriter, best known as the son of legendary E Street Band saxophonist Clarence Clemons and for leading his own rock and soul projects.
-
E.
Blake Tekotte
Blake Tekotte is an American former professional baseball outfielder who played in Major League Baseball, primarily known for his time with the San Diego Padres.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Pene Delmage Triple: [Albert Finney, spouse, Pene Delmage]
Generated description
Pene Delmage is a British travel agent and the widow of acclaimed English actor Albert Finney.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pene Delmage Target entity description: Pene Delmage is a British travel agent and the widow of acclaimed English actor Albert Finney.
-
A.
Lance LePere
Lance LePere is an American fashion designer and longtime creative collaborator best known as the husband of designer Michael Kors.
-
B.
Donnel Pumphrey
Donnel Pumphrey is an American former running back best known for his record-setting college career at San Diego State University, where he became the NCAA's all-time leading rusher.
-
C.
Alann Lopes
Alann Lopes is an entrepreneur and founder associated with the educational organization Sally Ride Science.
-
D.
Nick Clemons
Nick Clemons is an American musician and singer-songwriter, best known as the son of legendary E Street Band saxophonist Clarence Clemons and for leading his own rock and soul projects.
-
E.
Blake Tekotte
Blake Tekotte is an American former professional baseball outfielder who played in Major League Baseball, primarily known for his time with the San Diego Padres.
- F. None of above. chosen
Provenance (5 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada6e8e4b48190bc7c6443fc6da900 |
completed | March 8, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e81e6f98819099317f97f0c7f546 |
completed | March 12, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_69b2ec48bf888190a5eeac0aa2cc50c3 |
completed | March 12, 2026, 4:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2ecd134e88190933e52d7f1f5be2a |
completed | March 12, 2026, 4:41 p.m. |
Created at: March 8, 2026, 3:07 p.m.