Triple
T17578639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathleen High School |
E428138
|
entity |
| Predicate | hasNotableAlumnus |
P51
|
FINISHED |
| Object |
Maurice Crum Jr.
Maurice Crum Jr. is a former American football linebacker best known for his standout collegiate career with the Notre Dame Fighting Irish.
|
E1277089
|
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: Maurice Crum Jr. | Statement: [Kathleen High School, hasNotableAlumnus, Maurice Crum Jr.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maurice Crum Jr. Context triple: [Kathleen High School, hasNotableAlumnus, Maurice Crum Jr.]
-
A.
Maurice Moore
Maurice Moore was a colonial-era figure known for establishing the settlement that became Brunswick Town in what is now North Carolina.
-
B.
Maurice McEndree
Maurice McEndree is a cinematographer known for his work on the film "Faces."
-
C.
Maurice McEndree
Maurice McEndree is a music producer best known for his work on the track "Shadows."
-
D.
Maurice Scott
Maurice Scott is a reality television personality best known for appearing as a cast member on the OWN series "Love & Marriage: Huntsville."
-
E.
Maurice Phillips
Maurice Phillips was a British film and television director known for his work on dramas and thrillers, including the feature film "Another You."
- 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: Maurice Crum Jr. Triple: [Kathleen High School, hasNotableAlumnus, Maurice Crum Jr.]
Generated description
Maurice Crum Jr. is a former American football linebacker best known for his standout collegiate career with the Notre Dame Fighting Irish.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Maurice Crum Jr. Target entity description: Maurice Crum Jr. is a former American football linebacker best known for his standout collegiate career with the Notre Dame Fighting Irish.
-
A.
Maurice Moore
Maurice Moore was a colonial-era figure known for establishing the settlement that became Brunswick Town in what is now North Carolina.
-
B.
Maurice McEndree
Maurice McEndree is a cinematographer known for his work on the film "Faces."
-
C.
Maurice McEndree
Maurice McEndree is a music producer best known for his work on the track "Shadows."
-
D.
Maurice Scott
Maurice Scott is a reality television personality best known for appearing as a cast member on the OWN series "Love & Marriage: Huntsville."
-
E.
Maurice Phillips
Maurice Phillips was a British film and television director known for his work on dramas and thrillers, including the feature film "Another You."
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463cb40088190b726f2c026358cf2 |
completed | April 19, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01ddebfec88190a6783388521faf57 |
completed | May 11, 2026, 1:47 p.m. |
| NEDg | Description generation | batch_6a01e2779a2c8190ab895dd0399b40e1 |
completed | May 11, 2026, 2:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01e30e76548190a51ff1ee870c563f |
completed | May 11, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:50 a.m.