Triple
T18445891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliza Sommers |
E450655
|
entity |
| Predicate | undertakes |
P16081
|
FINISHED |
| Object | perilous journey |
—
|
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: perilous journey | Statement: [Eliza Sommers, undertakes, perilous journey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undertakes Context triple: [Eliza Sommers, undertakes, perilous journey]
-
A.
undertook
chosen
Indicates that an entity assumed responsibility for starting and carrying out a task, project, or action.
-
B.
undertakenAs
Indicates that an action, task, or responsibility is performed or carried out in the capacity, role, or form of a specified entity.
-
C.
takes
Indicates that one entity receives, accepts, or comes into possession of another entity.
-
D.
undergoing
Indicates that an entity is currently experiencing, being subjected to, or in the process of a particular action, change, or treatment.
-
E.
underwent
Indicates that an entity experienced or was subjected to a process, event, or change, typically as the patient of an action.
- 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_69d8d38345688190b565eac2e4cd7935 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51c15127881909d23b6dd45d7ccc9 |
completed | April 19, 2026, 6:16 p.m. |
| PD | Predicate disambiguation | batch_69e469c943a4819094c8fdc5971ad3a7 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:30 a.m.