Triple
T16747402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DOI |
E406990
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Handle System |
E68554
|
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: Handle System | Statement: [DOI, relatedTo, Handle System]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Handle System Context triple: [DOI, relatedTo, Handle System]
-
A.
Handle System
chosen
The Handle System is a global, distributed identifier system designed to provide persistent, secure, and scalable resolution of digital object identifiers on the internet.
-
B.
System
System is a core .NET namespace that provides fundamental classes and base types essential for building .NET applications.
-
C.
System1
System1 is a digital marketing and customer acquisition company specializing in data-driven advertising and online performance-based media.
-
D.
Sistema
Sistema is a consumer food storage and kitchenware brand known for its reusable plastic containers and lunch solutions.
-
E.
Handle
Handle is a dynamic, wheeled-legged robot developed by Boston Dynamics for agile material handling and warehouse automation tasks.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3aa2439848190a86a5bfc0702e2fe |
completed | April 18, 2026, 3:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00aaf3c6088190a8301a9613d74474 |
completed | May 10, 2026, 3:57 p.m. |
Created at: April 10, 2026, 5:21 a.m.