Triple
T7667346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USA Baseball National Training Complex |
E173655
|
entity |
| Predicate | hasFieldCount |
P36398
|
FINISHED |
| Object | 4 regulation-size baseball fields |
—
|
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: 4 regulation-size baseball fields | Statement: [USA Baseball National Training Complex, hasFieldCount, 4 regulation-size baseball fields]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFieldCount Context triple: [USA Baseball National Training Complex, hasFieldCount, 4 regulation-size baseball fields]
-
A.
hasNumberOfFields
chosen
Indicates the specific count of fields or distinct data elements that an entity possesses.
-
B.
hasFieldLength
Indicates that an entity possesses a field whose length (such as number of characters or size) is specified or constrained.
-
C.
hasDataFields
Indicates that an entity possesses or is associated with specific data fields or attributes.
-
D.
hasColumnCountBack
Indicates that an entity (such as a table or layout) has a specified number of columns on its back side or rear-facing section.
-
E.
hasFieldName
Indicates that one entity is associated with, or identified by, a specific field name in a data structure or schema.
- 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_69c699562484819086752091e3164a27 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7063dab1881909598b04999b8b690 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015f7430819099d3ea2781b7cee2 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 4 p.m.