Triple
T21335312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gail Berke |
E526028
|
entity |
| Predicate | romanticPartner |
P9994
|
FINISHED |
| Object |
David Sanders
David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
|
E1478325
|
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: David Sanders | Statement: [Gail Berke, romanticPartner, David Sanders]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Sanders Context triple: [Gail Berke, romanticPartner, David Sanders]
-
A.
David Sanders
David Sanders is the protagonist of the thriller novel "The Deep," around whom the story’s central mystery and underwater adventure revolve.
-
B.
Thomas Sanders
Thomas Sanders was an American businessman and early telecommunications pioneer who co-founded the company that became AT&T.
-
C.
Mark Sandler
Mark Sandler is a computer scientist and machine learning researcher known for his work on efficient deep neural network architectures, including the development of MobileNetV2.
-
D.
Barry Sandler
Barry Sandler is an American screenwriter and producer best known for his work on films such as "Making Love" and various adaptations and thrillers in the 1970s and 1980s.
-
E.
Marty Sanders
Marty Sanders is an American guitarist and singer best known as a longtime member of the 1960s pop-rock group Jay and the Americans.
- 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: David Sanders Triple: [Gail Berke, romanticPartner, David Sanders]
Generated description
David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Sanders Target entity description: David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
-
A.
David Sanders
David Sanders is the protagonist of the thriller novel "The Deep," around whom the story’s central mystery and underwater adventure revolve.
-
B.
Thomas Sanders
Thomas Sanders was an American businessman and early telecommunications pioneer who co-founded the company that became AT&T.
-
C.
Mark Sandler
Mark Sandler is a computer scientist and machine learning researcher known for his work on efficient deep neural network architectures, including the development of MobileNetV2.
-
D.
Barry Sandler
Barry Sandler is an American screenwriter and producer best known for his work on films such as "Making Love" and various adaptations and thrillers in the 1970s and 1980s.
-
E.
Marty Sanders
Marty Sanders is an American guitarist and singer best known as a longtime member of the 1960s pop-rock group Jay and the Americans.
- 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_69e0b51c33048190ab27cede74ef798c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e898d6fcbc8190b83d9cfc9b4ca123 |
completed | April 22, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09a5c07438819084e08576a703406c |
completed | May 17, 2026, 11:25 a.m. |
| NEDg | Description generation | batch_6a09a6723714819087d80d62bdcb3926 |
completed | May 17, 2026, 11:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09a6d55bf08190bb4a90fbb258f49b |
completed | May 17, 2026, 11:30 a.m. |
Created at: April 16, 2026, 4:43 p.m.