Triple
T3547231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Haise |
E75024
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object |
Thomas Haise
Thomas Haise is known primarily as the son of American astronaut and Apollo 13 lunar module pilot Fred Haise.
|
E367576
|
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: Thomas Haise | Statement: [Fred Haise, child, Thomas Haise]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Haise Context triple: [Fred Haise, child, Thomas Haise]
-
A.
Charles Haid
Charles Haid is an American actor and director best known for his role as Officer Andy Renko on the television series "Hill Street Blues."
-
B.
John Boies Tileston
John Boies Tileston was an early mountaineer known for making the first recorded ascent of Mount Lyell, the highest peak in Yosemite National Park.
-
C.
John Requa
John Requa is an American screenwriter and director known for co-writing films such as "Bad Santa," "I Love You Phillip Morris," and "Jungle Cruise."
-
D.
Christopher Parsons
Christopher Parsons was a British wildlife film producer and director renowned for his pioneering work on nature documentaries, particularly with the BBC Natural History Unit.
-
E.
Douglas Wick
Douglas Wick is an American film producer known for acclaimed movies such as "Gladiator," "Working Girl," and "Memoirs of a Geisha."
- 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: Thomas Haise Triple: [Fred Haise, child, Thomas Haise]
Generated description
Thomas Haise is known primarily as the son of American astronaut and Apollo 13 lunar module pilot Fred Haise.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Thomas Haise Target entity description: Thomas Haise is known primarily as the son of American astronaut and Apollo 13 lunar module pilot Fred Haise.
-
A.
Charles Haid
Charles Haid is an American actor and director best known for his role as Officer Andy Renko on the television series "Hill Street Blues."
-
B.
John Boies Tileston
John Boies Tileston was an early mountaineer known for making the first recorded ascent of Mount Lyell, the highest peak in Yosemite National Park.
-
C.
John Requa
John Requa is an American screenwriter and director known for co-writing films such as "Bad Santa," "I Love You Phillip Morris," and "Jungle Cruise."
-
D.
Christopher Parsons
Christopher Parsons was a British wildlife film producer and director renowned for his pioneering work on nature documentaries, particularly with the BBC Natural History Unit.
-
E.
Douglas Wick
Douglas Wick is an American film producer known for acclaimed movies such as "Gladiator," "Working Girl," and "Memoirs of a Geisha."
- 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbfd0eb6081908f1380db4cfade87 |
completed | March 8, 2026, 6:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38be582308190808274c8a530ce51 |
completed | March 13, 2026, 4 a.m. |
| NEDg | Description generation | batch_69b38c6dbfcc8190897d0c12e8ce4416 |
completed | March 13, 2026, 4:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b38cf9d8188190adb91671d062a6f9 |
completed | March 13, 2026, 4:05 a.m. |
Created at: March 8, 2026, 3:20 p.m.