Triple
T29910541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NameDrop |
E759667
|
entity |
| Predicate | supportsInteractionBetween |
P115265
|
FINISHED |
| Object |
iPhone and Apple Watch
iPhone and Apple Watch are Apple’s tightly integrated mobile devices that work together to deliver seamless communication, health tracking, and app experiences across wrist and phone.
|
E1890419
|
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: iPhone and Apple Watch | Statement: [NameDrop, supportsInteractionBetween, iPhone and Apple Watch]
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: iPhone and Apple Watch Triple: [NameDrop, supportsInteractionBetween, iPhone and Apple Watch]
Generated description
iPhone and Apple Watch are Apple’s tightly integrated mobile devices that work together to deliver seamless communication, health tracking, and app experiences across wrist and phone.
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_69f224600590819085e148a01c056ef6 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a03809725bc81909c8b61d72d72ca2b |
completed | May 12, 2026, 7:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a26f1f0392881909237df9458780070 |
completed | June 8, 2026, 4:46 p.m. |
| NEDg | Description generation | batch_6a26f3db3c4c8190afee1a0b06ade0fd |
completed | June 8, 2026, 4:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a26f4718864819095dcc8bc1083a6a2 |
completed | June 8, 2026, 4:57 p.m. |
Created at: April 29, 2026, 6:10 p.m.