Triple
T33660730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lydia Touchett |
E862343
|
entity |
| Predicate | offersTravelOpportunityTo |
P78710
|
FINISHED |
| Object | Isabel Archer |
—
|
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: Isabel Archer | Statement: [Lydia Touchett, offersTravelOpportunityTo, Isabel Archer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersTravelOpportunityTo Context triple: [Lydia Touchett, offersTravelOpportunityTo, Isabel Archer]
-
A.
offersOpportunity
chosen
Indicates that one entity provides another with a chance or possibility to do, obtain, or experience something.
-
B.
offersExchangeOpportunities
Indicates that one entity provides chances for another entity to participate in exchanges, such as trading, swapping, or reciprocal programs.
-
C.
boardingOffered
Indicates that the provision of boarding or lodging services is being made available to one or more entities.
-
D.
offersProcess
Indicates that one entity provides or makes available a particular process for use by another entity.
-
E.
offersConnectionTo
Indicates that one entity provides or enables access, linkage, or connectivity to 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_69f34984c4008190bb82f33a7819da64 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdb31800508190beec15adb9bbd292 |
completed | May 8, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69fdb19c381c8190bafb2f565da097f1 |
completed | May 8, 2026, 9:49 a.m. |
Created at: May 1, 2026, 1:42 a.m.