Triple
T7276772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irving Pichel |
E163049
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Vanda Hoff
Vanda Hoff was the wife of American actor and film director Irving Pichel.
|
E653820
|
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: Vanda Hoff | Statement: [Irving Pichel, spouse, Vanda Hoff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vanda Hoff Context triple: [Irving Pichel, spouse, Vanda Hoff]
-
A.
E. Hoffmeister
E. Hoffmeister was a music publisher active in the classical era, known for issuing works by prominent composers such as Beethoven.
-
B.
Gregori Aminoff
Gregori Aminoff was a Swedish mineralogist and crystallographer renowned for his contributions to crystal structure research and for having a prestigious Royal Swedish Academy of Sciences prize named in his honor.
-
C.
Henry Meybohm
Henry Meybohm was a mountaineer known for participating in the first ascent of Mount Hunter in Alaska.
-
D.
Soma Morgenstern
Soma Morgenstern was an Austrian-Jewish writer and journalist best known for his novels and memoirs depicting Jewish life in Eastern Europe and the impact of 20th-century upheavals.
-
E.
Gustav von Vaerst
Gustav von Vaerst was a German Wehrmacht general who commanded armored forces, including in the North African campaign during World War II.
- 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: Vanda Hoff Triple: [Irving Pichel, spouse, Vanda Hoff]
Generated description
Vanda Hoff was the wife of American actor and film director Irving Pichel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vanda Hoff Target entity description: Vanda Hoff was the wife of American actor and film director Irving Pichel.
-
A.
E. Hoffmeister
E. Hoffmeister was a music publisher active in the classical era, known for issuing works by prominent composers such as Beethoven.
-
B.
Gregori Aminoff
Gregori Aminoff was a Swedish mineralogist and crystallographer renowned for his contributions to crystal structure research and for having a prestigious Royal Swedish Academy of Sciences prize named in his honor.
-
C.
Henry Meybohm
Henry Meybohm was a mountaineer known for participating in the first ascent of Mount Hunter in Alaska.
-
D.
Soma Morgenstern
Soma Morgenstern was an Austrian-Jewish writer and journalist best known for his novels and memoirs depicting Jewish life in Eastern Europe and the impact of 20th-century upheavals.
-
E.
Gustav von Vaerst
Gustav von Vaerst was a German Wehrmacht general who commanded armored forces, including in the North African campaign during World War II.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb2f239c819097c1ac4d6de8b0e5 |
completed | March 27, 2026, 8:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db3110688190bf52180ea159c91c |
completed | March 28, 2026, 1:44 p.m. |
| NEDg | Description generation | batch_69c7dbf65fb08190ae8a9c4e57d42e97 |
completed | March 28, 2026, 1:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7dc6873a081908ea4e953430ec20b |
completed | March 28, 2026, 1:49 p.m. |
Created at: March 27, 2026, 2:59 p.m.