Triple
T12823798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Udonis Haslem |
E306596
|
entity |
| Predicate | wentUndraftedYear |
P10042
|
FINISHED |
| Object | 2002 |
—
|
LITERAL FINISHED |
How this triple was built (2 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: 2002 | Statement: [Udonis Haslem, wentUndraftedYear, 2002]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wentUndraftedYear Context triple: [Udonis Haslem, wentUndraftedYear, 2002]
-
A.
undraftedYear
chosen
Indicates the year in which an individual was eligible for a draft but was not selected by any team.
-
B.
signedAsUndraftedFreeAgentYear
Indicates the year in which an entity (typically an athlete) entered into a contract as an undrafted free agent.
-
C.
signedAsUndraftedFreeAgentBy
Indicates that a player joined a team by signing a contract as an undrafted free agent, rather than being selected in a draft.
-
D.
undrafted
Indicates that an entity, typically a player or candidate, was not selected during a formal drafting or selection process.
-
E.
yearDrafted
Indicates the specific year in which an entity (typically a person, such as an athlete or player) was selected or chosen in a formal draft process.
- F. None of above.
Provenance (3 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_69d7bdf46c448190b1faa55aaacb6317 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96edcc99c8190986cd78fe4714835 |
completed | April 10, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69d964100f7481909a197396003d4a71 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:32 p.m.