Triple
T7495298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene Dunne |
E177108
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Francis Griffin
Francis Griffin was the husband of acclaimed American actress and singer Irene Dunne.
|
E676506
|
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: Francis Griffin | Statement: [Irene Dunne, spouse, Francis Griffin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis Griffin Context triple: [Irene Dunne, spouse, Francis Griffin]
-
A.
Francis Griffin
Francis Griffin is a recurring character on the animated television series "Family Guy," known as Peter Griffin's stern, devoutly Catholic father.
-
B.
Douglas Guilfoyle
Douglas Guilfoyle is an international law scholar known for his work on the law of the sea, maritime security, and international criminal law.
-
C.
Philip Keenan
Philip Keenan was an American astronomer best known for co-developing the Morgan–Keenan (MK) stellar classification system that remains a standard in astrophysics.
-
D.
John Gilroy
John Gilroy is a film editor known for his work on major Hollywood productions, including the science-fiction monster film "Pacific Rim."
-
E.
Francis Bull
Francis Bull was a prominent Norwegian literary historian and critic who played a key role in shaping 20th-century Norwegian literary scholarship and language debates.
- 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: Francis Griffin Triple: [Irene Dunne, spouse, Francis Griffin]
Generated description
Francis Griffin was the husband of acclaimed American actress and singer Irene Dunne.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Francis Griffin Target entity description: Francis Griffin was the husband of acclaimed American actress and singer Irene Dunne.
-
A.
Francis Griffin
Francis Griffin is a recurring character on the animated television series "Family Guy," known as Peter Griffin's stern, devoutly Catholic father.
-
B.
Douglas Guilfoyle
Douglas Guilfoyle is an international law scholar known for his work on the law of the sea, maritime security, and international criminal law.
-
C.
Philip Keenan
Philip Keenan was an American astronomer best known for co-developing the Morgan–Keenan (MK) stellar classification system that remains a standard in astrophysics.
-
D.
John Gilroy
John Gilroy is a film editor known for his work on major Hollywood productions, including the science-fiction monster film "Pacific Rim."
-
E.
Francis Bull
Francis Bull was a prominent Norwegian literary historian and critic who played a key role in shaping 20th-century Norwegian literary scholarship and language debates.
- 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_69c69f2583808190bd1a4936c42a5815 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f57b5b4c8190ab839e6a98ee86ed |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8682f438c8190bca55f7773fe6838 |
completed | March 28, 2026, 11:45 p.m. |
| NEDg | Description generation | batch_69c868edf84c8190a6fefce18fc606e1 |
completed | March 28, 2026, 11:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c869c54ad08190ba42231080d0e9f3 |
completed | March 28, 2026, 11:52 p.m. |
Created at: March 27, 2026, 3:43 p.m.