Triple
T23841438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laws of Cricket |
E590996
|
entity |
| Predicate | includesLaw |
P116428
|
FINISHED |
| Object |
Law 22: Wide ball
Law 22: Wide ball is the cricket rule that defines when a delivery is too wide or high for the batter to hit under normal play, resulting in an extra run to the batting side.
|
E1605008
|
NE 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: Law 22: Wide ball | Statement: [Laws of Cricket, includesLaw, Law 22: Wide ball]
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: Law 22: Wide ball Triple: [Laws of Cricket, includesLaw, Law 22: Wide ball]
Generated description
Law 22: Wide ball is the cricket rule that defines when a delivery is too wide or high for the batter to hit under normal play, resulting in an extra run to the batting side.
Provenance (5 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c88797d4819081831fd3f8822ef4 |
completed | April 29, 2026, 8:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0f69a70c6c8190a052975577170056 |
completed | May 21, 2026, 8:23 p.m. |
| NEDg | Description generation | batch_6a0f6d40d1108190b4da250e40014008 |
completed | May 21, 2026, 8:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0f6e2ff6c481909b81c0d31259a919 |
completed | May 21, 2026, 8:42 p.m. |
Created at: April 17, 2026, 8:08 p.m.