Triple
T335078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Mann |
E6705
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object |
Carla Mann
Carla Mann was a German actress and the sister of Nobel Prize–winning author Thomas Mann.
|
E131780
|
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: Carla Mann | Statement: [Thomas Mann, relative, Carla Mann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carla Mann Context triple: [Thomas Mann, relative, Carla Mann]
-
A.
Nancy Carlson
Nancy Carlson is known as the wife of World Wide Web inventor Sir Tim Berners-Lee.
-
B.
Julie Packard
Julie Packard is a marine biologist and conservationist best known as the founding executive director of the Monterey Bay Aquarium and a prominent advocate for ocean conservation.
-
C.
Joanne Rogers
Joanne Rogers was an American concert pianist and television personality best known as the longtime wife and collaborator of children's television icon Fred Rogers and as a prominent advocate for his legacy.
-
D.
Susannah Martin
Susannah Martin was a Massachusetts woman executed for alleged witchcraft in 1692, remembered as one of the victims of the Salem witch trials.
-
E.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
- 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: Carla Mann Triple: [Thomas Mann, relative, Carla Mann]
Generated description
Carla Mann was a German actress and the sister of Nobel Prize–winning author Thomas Mann.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carla Mann Target entity description: Carla Mann was a German actress and the sister of Nobel Prize–winning author Thomas Mann.
-
A.
Nancy Carlson
Nancy Carlson is known as the wife of World Wide Web inventor Sir Tim Berners-Lee.
-
B.
Julie Packard
Julie Packard is a marine biologist and conservationist best known as the founding executive director of the Monterey Bay Aquarium and a prominent advocate for ocean conservation.
-
C.
Joanne Rogers
Joanne Rogers was an American concert pianist and television personality best known as the longtime wife and collaborator of children's television icon Fred Rogers and as a prominent advocate for his legacy.
-
D.
Susannah Martin
Susannah Martin was a Massachusetts woman executed for alleged witchcraft in 1692, remembered as one of the victims of the Salem witch trials.
-
E.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
- 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eac81c0c8190b3cb0d53b1cf62b5 |
completed | Feb. 28, 2026, 1:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac5e8f412c8190a50bfd63ce435663 |
completed | March 7, 2026, 5:21 p.m. |
| NEDg | Description generation | batch_69ac5f3b0ee8819094ba1bdbaac8c43d |
completed | March 7, 2026, 5:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac5fa6a43881908b0ac30c4e376c5b |
completed | March 7, 2026, 5:25 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.