Triple
T1866908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMTP AUTH |
E34941
|
entity |
| Predicate | advertisedBy |
P4613
|
FINISHED |
| Object | ESMTP |
—
|
LITERAL 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: ESMTP | Statement: [SMTP AUTH, advertisedBy, ESMTP]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: advertisedBy Context triple: [SMTP AUTH, advertisedBy, ESMTP]
-
A.
advertises
Indicates that one entity promotes, publicizes, or markets another entity, typically to attract attention or customers.
-
B.
brokeredBy
Indicates that an intermediary agent or organization arranged, facilitated, or negotiated the relationship, transaction, or agreement between the involved entities.
-
C.
acquisitionAnnouncedBy
Indicates that an acquisition event was publicly announced by the specified announcing entity (such as a company or organization).
-
D.
mediaAffiliate
Indicates a relationship where one media entity is affiliated with, partnered to, or formally associated with another media organization or outlet.
-
E.
marketedBy
chosen
Indicates that one entity is promoted, advertised, or commercially presented to customers by another entity.
- F. None of above.
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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb16c09e48190a345c95eab59fd87 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe02c3c819093a4744b476106ca |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.