Triple
T14901325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Graves |
E360009
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Joan Endress
Joan Endress is best known as the longtime wife of American actor Peter Graves, star of the original "Mission: Impossible" television series.
|
E1244118
|
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: Joan Endress | Statement: [Peter Graves, spouse, Joan Endress]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan Endress Context triple: [Peter Graves, spouse, Joan Endress]
-
A.
Joan A. Brennecke
Joan A. Brennecke is a prominent chemical engineer renowned for her pioneering research on ionic liquids and sustainable chemical processes, recognized as one of the leading figures in green chemistry.
-
B.
Margaret Rudman
Margaret Rudman is known as the wife of the late U.S. Senator Warren Rudman of New Hampshire.
-
C.
Mary Patricia Plangman
Mary Patricia Plangman is the birth name of Patricia Highsmith, the acclaimed American novelist best known for her psychological thrillers and the Tom Ripley series.
-
D.
Joan E. Chapman
Joan E. Chapman is a film editor known for her work on the action movie "First Blood."
-
E.
Eileen Heisler
Eileen Heisler is an American television writer and producer best known for co-creating the series Lipstick Jungle and The Middle.
- 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: Joan Endress Triple: [Peter Graves, spouse, Joan Endress]
Generated description
Joan Endress is best known as the longtime wife of American actor Peter Graves, star of the original "Mission: Impossible" television series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joan Endress Target entity description: Joan Endress is best known as the longtime wife of American actor Peter Graves, star of the original "Mission: Impossible" television series.
-
A.
Joan A. Brennecke
Joan A. Brennecke is a prominent chemical engineer renowned for her pioneering research on ionic liquids and sustainable chemical processes, recognized as one of the leading figures in green chemistry.
-
B.
Margaret Rudman
Margaret Rudman is known as the wife of the late U.S. Senator Warren Rudman of New Hampshire.
-
C.
Mary Patricia Plangman
Mary Patricia Plangman is the birth name of Patricia Highsmith, the acclaimed American novelist best known for her psychological thrillers and the Tom Ripley series.
-
D.
Joan E. Chapman
Joan E. Chapman is a film editor known for her work on the action movie "First Blood."
-
E.
Eileen Heisler
Eileen Heisler is an American television writer and producer best known for co-creating the series Lipstick Jungle and The Middle.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded609bf68819099ca3aa3fe1acadc |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dbf2567c81909ab6054ade27afac |
completed | May 10, 2026, 7:26 p.m. |
| NEDg | Description generation | batch_6a0114d33cac819083d8e542ea5bc274 |
completed | May 10, 2026, 11:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0115c583608190bf07ac205399f253 |
completed | May 10, 2026, 11:33 p.m. |
Created at: April 10, 2026, 2:11 a.m.