Triple
T21638807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalker |
E534032
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Travis Schuldt
Travis Schuldt is an American actor best known for his roles on the sitcom "Scrubs" and various television dramas and films.
|
E1493826
|
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: Travis Schuldt | Statement: [Stalker, starring, Travis Schuldt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Travis Schuldt Context triple: [Stalker, starring, Travis Schuldt]
-
A.
Trent Baalke
Trent Baalke is an American football executive best known for his tenure as an NFL general manager, including leading front offices for multiple franchises.
-
B.
Travis Rogers
Travis Rogers is a musical artist known for his featured performance on the track "Live Today."
-
C.
Trent Willmon
Trent Willmon is an American country music singer-songwriter known for both his own recordings and for writing songs for other prominent country artists.
-
D.
Travis Clark
Travis Clark is a songwriter known for contributing to the track "Head Above Water."
-
E.
Brett Keisel
Brett Keisel is a former NFL defensive end best known for his long career with the Pittsburgh Steelers, where he became a key member of their dominant 2000s defense and a fan favorite.
- 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: Travis Schuldt Triple: [Stalker, starring, Travis Schuldt]
Generated description
Travis Schuldt is an American actor best known for his roles on the sitcom "Scrubs" and various television dramas and films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Travis Schuldt Target entity description: Travis Schuldt is an American actor best known for his roles on the sitcom "Scrubs" and various television dramas and films.
-
A.
Trent Baalke
Trent Baalke is an American football executive best known for his tenure as an NFL general manager, including leading front offices for multiple franchises.
-
B.
Travis Rogers
Travis Rogers is a musical artist known for his featured performance on the track "Live Today."
-
C.
Trent Willmon
Trent Willmon is an American country music singer-songwriter known for both his own recordings and for writing songs for other prominent country artists.
-
D.
Travis Clark
Travis Clark is a songwriter known for contributing to the track "Head Above Water."
-
E.
Brett Keisel
Brett Keisel is a former NFL defensive end best known for his long career with the Pittsburgh Steelers, where he became a key member of their dominant 2000s defense and a fan favorite.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef538fb12481908f70ad8dbe1d99e4 |
completed | April 27, 2026, 12:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a0fa04cd481909a9a9d7420646e00 |
completed | May 17, 2026, 6:57 p.m. |
| NEDg | Description generation | batch_6a0a10d3dd8081909f2370db4a3cb527 |
completed | May 17, 2026, 7:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a1143621881908af17d96a1759f9a |
completed | May 17, 2026, 7:04 p.m. |
Created at: April 16, 2026, 6:35 p.m.