Triple
T5643155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gypsy Rose Lee |
E124316
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Alexander Kirkland
Alexander Kirkland was an American actor active in the early to mid-20th century, known for his work on stage and in films.
|
E537259
|
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: Alexander Kirkland | Statement: [Gypsy Rose Lee, spouse, Alexander Kirkland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alexander Kirkland Context triple: [Gypsy Rose Lee, spouse, Alexander Kirkland]
-
A.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
-
B.
Angus Mullens
Angus Mullens is the central protagonist of the film "Starstruck," around whom the story’s main events and character developments revolve.
-
C.
Ryan McIntyre
Ryan McIntyre is an American entrepreneur and venture capitalist best known as a co-founder of the early internet search company Excite.
-
D.
Jason Keller
Jason Keller is an American screenwriter best known for co-writing the racing drama film "Ford v Ferrari."
-
E.
Kevin Griswold
Kevin Griswold is a character in the 2015 comedy film "Vacation," appearing as a member of the extended Griswold family in the franchise’s reboot.
- 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: Alexander Kirkland Triple: [Gypsy Rose Lee, spouse, Alexander Kirkland]
Generated description
Alexander Kirkland was an American actor active in the early to mid-20th century, known for his work on stage and in films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alexander Kirkland Target entity description: Alexander Kirkland was an American actor active in the early to mid-20th century, known for his work on stage and in films.
-
A.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
-
B.
Angus Mullens
Angus Mullens is the central protagonist of the film "Starstruck," around whom the story’s main events and character developments revolve.
-
C.
Ryan McIntyre
Ryan McIntyre is an American entrepreneur and venture capitalist best known as a co-founder of the early internet search company Excite.
-
D.
Jason Keller
Jason Keller is an American screenwriter best known for co-writing the racing drama film "Ford v Ferrari."
-
E.
Kevin Griswold
Kevin Griswold is a character in the 2015 comedy film "Vacation," appearing as a member of the extended Griswold family in the franchise’s reboot.
- 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_69c00824643c81909ffdb888a2d35189 |
completed | March 22, 2026, 3:17 p.m. |
| NER | Named-entity recognition | batch_69c022a7cd9c819087f86f60e8b65fc3 |
completed | March 22, 2026, 5:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04d80396c81909e26da3b5ca5ea34 |
completed | March 22, 2026, 8:13 p.m. |
| NEDg | Description generation | batch_69c04edbf1f081908d74d0ac29601a35 |
completed | March 22, 2026, 8:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c04f7e64c88190bbced2f2460c1913 |
completed | March 22, 2026, 8:22 p.m. |
Created at: March 22, 2026, 3:41 p.m.