Triple
T2341181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | US Open (tennis) |
E45029
|
entity |
| Predicate | courtMaterial |
P38839
|
FINISHED |
| Object | acrylic hard court |
—
|
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: acrylic hard court | Statement: [US Open (tennis), courtMaterial, acrylic hard court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtMaterial Context triple: [US Open (tennis), courtMaterial, acrylic hard court]
-
A.
courtContext
Indicates the legal or judicial setting, circumstances, or framework within which a court-related action or relationship takes place.
-
B.
courtroom
Indicates a relationship where a legal proceeding or judicial action takes place within or is associated with a specific courtroom.
-
C.
courtOfficial
Indicates that an entity serves in an official capacity within a court, holding an authorized role in judicial or legal proceedings.
-
D.
judicialArticle
Indicates that there is a specific legal or judicial article that governs, defines, or is applied to the relationship or action between the entities.
-
E.
courtReported
Indicates that a court’s decision, proceedings, or judgment have been formally documented and made publicly available in a report or record.
- F. None of above. chosen
Provenance (4 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_69a88917935081909b755dbf38e81024 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abcade3c808190ab3803538ccbe620 |
completed | March 7, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69abc59616a8819099711834e6f1ccd6 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcadd2a0c8190b6973d390e98bd66 |
completed | March 7, 2026, 6:51 a.m. |
Created at: March 4, 2026, 7:52 p.m.