Triple
T17361675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mourning |
E422080
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object |
Trey Mourning
Trey Mourning is an American professional basketball player and the son of Hall of Famer Alonzo Mourning.
|
E1265868
|
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: Trey Mourning | Statement: [Mourning, usedBy, Trey Mourning]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trey Mourning Context triple: [Mourning, usedBy, Trey Mourning]
-
A.
Trey Kemp
Trey Kemp is a golf course architect known for designing and renovating courses such as Stevens Park Golf Course.
-
B.
DeVon Harris
DeVon Harris is a songwriter best known for his work on the track "So High."
-
C.
Glen Rice
Glen Rice is a former American professional basketball player best known as a sharpshooting forward who starred at the University of Michigan before enjoying a successful NBA career, including three All-Star selections and an NBA championship.
-
D.
Tim Weatherspoon
Tim Weatherspoon is an American talent manager best known as the husband of singer and former Destiny’s Child member Kelly Rowland.
-
E.
John Starks
John Starks is a former NBA shooting guard best known for his time with the New York Knicks in the 1990s, where he became an All-Star and a fan favorite for his intense defense and clutch shooting.
- 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: Trey Mourning Triple: [Mourning, usedBy, Trey Mourning]
Generated description
Trey Mourning is an American professional basketball player and the son of Hall of Famer Alonzo Mourning.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Trey Mourning Target entity description: Trey Mourning is an American professional basketball player and the son of Hall of Famer Alonzo Mourning.
-
A.
Trey Kemp
Trey Kemp is a golf course architect known for designing and renovating courses such as Stevens Park Golf Course.
-
B.
DeVon Harris
DeVon Harris is a songwriter best known for his work on the track "So High."
-
C.
Glen Rice
Glen Rice is a former American professional basketball player best known as a sharpshooting forward who starred at the University of Michigan before enjoying a successful NBA career, including three All-Star selections and an NBA championship.
-
D.
Tim Weatherspoon
Tim Weatherspoon is an American talent manager best known as the husband of singer and former Destiny’s Child member Kelly Rowland.
-
E.
John Starks
John Starks is a former NBA shooting guard best known for his time with the New York Knicks in the 1990s, where he became an All-Star and a fan favorite for his intense defense and clutch shooting.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4d6de88190b816b93ff5778157 |
completed | April 19, 2026, 2:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a019feb98b08190892e6477e51e1874 |
completed | May 11, 2026, 9:22 a.m. |
| NEDg | Description generation | batch_6a01a11885608190a073c2c1c53860ed |
completed | May 11, 2026, 9:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01a17c0acc8190a556b68fbcefaa76 |
completed | May 11, 2026, 9:29 a.m. |
Created at: April 10, 2026, 5:44 a.m.