Triple
T17687225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrews |
E440925
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Mark Andrews
Mark Andrews is an American football tight end for the Baltimore Ravens in the NFL, known as one of the league’s top receiving tight ends.
|
E819209
|
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: Mark Andrews | Statement: [Andrews, hasNotableBearer, Mark Andrews]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Andrews Context triple: [Andrews, hasNotableBearer, Mark Andrews]
-
A.
Mark Andrews
Mark Andrews is an American filmmaker best known for co-directing Pixar’s Academy Award–winning animated feature "Brave."
-
B.
Mark Andrews
Mark Andrews is a songwriter best known for co-writing the DMX track "What These Bitches Want."
-
C.
Mark Andrews
Mark Andrews is an American football tight end in the NFL, best known for his Pro Bowl performances with the Baltimore Ravens.
-
D.
Jerome Tang
Jerome Tang is an American college basketball coach best known for revitalizing the Kansas State Wildcats men's basketball program after a long tenure as an assistant at Baylor.
-
E.
Earl Thomas
Earl Thomas is a former NFL free safety best known as a cornerstone of the Seattle Seahawks' "Legion of Boom" defense and a key contributor to their Super Bowl XLVIII championship.
- 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: Mark Andrews Triple: [Andrews, hasNotableBearer, Mark Andrews]
Generated description
Mark Andrews is an American football tight end for the Baltimore Ravens in the NFL, known as one of the league’s top receiving tight ends.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Andrews Target entity description: Mark Andrews is an American football tight end for the Baltimore Ravens in the NFL, known as one of the league’s top receiving tight ends.
-
A.
Mark Andrews
Mark Andrews is an American filmmaker best known for co-directing Pixar’s Academy Award–winning animated feature "Brave."
-
B.
Mark Andrews
Mark Andrews is a songwriter best known for co-writing the DMX track "What These Bitches Want."
-
C.
Mark Andrews
chosen
Mark Andrews is an American football tight end in the NFL, best known for his Pro Bowl performances with the Baltimore Ravens.
-
D.
Jerome Tang
Jerome Tang is an American college basketball coach best known for revitalizing the Kansas State Wildcats men's basketball program after a long tenure as an assistant at Baylor.
-
E.
Earl Thomas
Earl Thomas is a former NFL free safety best known as a cornerstone of the Seattle Seahawks' "Legion of Boom" defense and a key contributor to their Super Bowl XLVIII championship.
- F. None of above.
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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e470488c4081909b747313ef97b69c |
completed | April 19, 2026, 6:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02232e1b4481908e8a89f2c1c244f1 |
completed | May 11, 2026, 6:42 p.m. |
| NEDg | Description generation | batch_6a0224e2403881909a6f86bcad4ce7b3 |
completed | May 11, 2026, 6:50 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a02254cbd3c8190afca986f066a60d2 |
completed | May 11, 2026, 6:51 p.m. |
Created at: April 10, 2026, 10:03 a.m.