Triple
T7891020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mikal Bridges |
E183232
|
entity |
| Predicate | tradeEvent |
P44956
|
FINISHED |
| Object | Traded on draft night 2018 from Philadelphia 76ers to Phoenix Suns |
—
|
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: Traded on draft night 2018 from Philadelphia 76ers to Phoenix Suns | Statement: [Mikal Bridges, tradeEvent, Traded on draft night 2018 from Philadelphia 76ers to Phoenix Suns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tradeEvent Context triple: [Mikal Bridges, tradeEvent, Traded on draft night 2018 from Philadelphia 76ers to Phoenix Suns]
-
A.
tradeSystem
Indicates a system or framework through which goods, services, or assets are exchanged between parties under defined rules or mechanisms.
-
B.
transferEvent
chosen
Indicates an event in which something is moved, handed over, or reassigned from one entity to another.
-
C.
tradeFocus
Indicates a primary emphasis on or specialization in a particular type of trade, transaction, or commercial activity within the relationship or context.
-
D.
tradeMechanism
Indicates the method or system through which a trade or exchange between parties is conducted.
-
E.
trades
Indicates an exchange relationship where one party gives something of value to another in return for something else of value.
- 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_69ca828c474c8190a254d6499871eaff |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39ee137081908e87e35016c3a176 |
completed | March 31, 2026, 3:05 a.m. |
| PD | Predicate disambiguation | batch_69cae92b0cd881908e715a10d3252e83 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5 p.m.