Triple
T23312945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ebXML |
E590629
|
entity |
| Predicate | component |
P35
|
FINISHED |
| Object | ebXML Registry |
—
|
NE NERFINISHED |
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: ebXML Registry | Statement: [ebXML, component, ebXML Registry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ebXML Registry Context triple: [ebXML, component, ebXML Registry]
-
A.
ebXML
chosen
ebXML (Electronic Business using eXtensible Markup Language) is a modular suite of open standards that enables secure, interoperable electronic business information exchange over the internet.
-
B.
UDDI
UDDI (Universal Description, Discovery, and Integration) is a platform-independent, XML-based registry standard for publishing and discovering web services on the internet.
-
C.
AXB
AXB is the ICAO airline designator assigned to Air India Express, the Indian low-cost carrier.
-
D.
XBRL
XBRL (eXtensible Business Reporting Language) is an XML-based global standard for tagging and exchanging business and financial data in a structured, machine-readable format.
-
E.
ESB
ESB is a flagship premium bitter ale produced by Fuller’s Griffin Brewery in London, renowned for its rich, malty character and multiple award wins.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1972ca70481909e2415c65964210a |
completed | April 29, 2026, 5:29 a.m. |
Created at: April 17, 2026, 5:06 p.m.