Triple
T22932192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EFetch |
E569469
|
entity |
| Predicate | relatedService |
P12758
|
FINISHED |
| Object | ELink |
—
|
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: ELink | Statement: [EFetch, relatedService, ELink]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ELink Context triple: [EFetch, relatedService, ELink]
-
A.
ELink
chosen
ELink is an NCBI E-utilities tool that retrieves and navigates links between related records across NCBI databases.
-
B.
Getlink
Getlink is a French-based company that owns and operates the infrastructure of the Channel Tunnel rail link between the United Kingdom and continental Europe.
-
C.
Fieldlink
Fieldlink was an early digital payments and security startup co-founded by Max Levchin that later evolved into the company behind PayPal.
-
D.
LINK
LINK is the radio callsign used by the Irish regional airline Airlink for air traffic control communications.
-
E.
XLink
XLink is an XML standard that extends basic linking capabilities by enabling rich, multidirectional, and metadata-enhanced hyperlinks between resources.
- 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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1813260608190bb9e1ca704c7e12f |
completed | April 29, 2026, 3:55 a.m. |
Created at: April 17, 2026, 3:44 p.m.