Triple
T23980833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2003 Major League Baseball season |
E604501
|
entity |
| Predicate | RookieOfTheYear_AL |
P38562
|
FINISHED |
| Object |
Angel Berroa
Angel Berroa is a former Dominican shortstop best known for his standout rookie year with the Kansas City Royals, which earned him the American League Rookie of the Year award in 2003.
|
E1627998
|
NE FINISHED |
How this triple was built (3 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: Angel Berroa | Statement: [2003 Major League Baseball season, RookieOfTheYear_AL, Angel Berroa]
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: Angel Berroa Triple: [2003 Major League Baseball season, RookieOfTheYear_AL, Angel Berroa]
Generated description
Angel Berroa is a former Dominican shortstop best known for his standout rookie year with the Kansas City Royals, which earned him the American League Rookie of the Year award in 2003.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RookieOfTheYear_AL Context triple: [2003 Major League Baseball season, RookieOfTheYear_AL, Angel Berroa]
-
A.
RookieOfTheYearYear
chosen
Indicates that the specified year is the season in which the entity was awarded the Rookie of the Year honor.
-
B.
RookieOfTheYearWinner
Indicates that the subject is the recipient of a Rookie of the Year award in a given league, season, or context.
-
C.
rookieOfTheYearLeague
Indicates that an entity was awarded the Rookie of the Year title in a specified sports league.
-
D.
rookieOfTheYearTrophy
Indicates that an entity has been awarded the Rookie of the Year trophy in a particular league, season, or competition.
-
E.
sharedRookieOfTheYearWith
Indicates that two entities were both awarded Rookie of the Year in the same season or context.
- F. None of above.
Provenance (6 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_69e29543f40c819087700b7a272afb60 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d2bd58448190a64e7a9020109229 |
completed | April 29, 2026, 9:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0fc9981d5881909d9602e515fdb957 |
completed | May 22, 2026, 3:12 a.m. |
| NEDg | Description generation | batch_6a0fcb0d718c81909c02cea23a2bffdc |
completed | May 22, 2026, 3:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0fcbdbc134819095ad50771a7c8809 |
completed | May 22, 2026, 3:22 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:27 p.m.