Triple
T12884903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maggie Tulliver has a close relationship with Philip Wakem |
E308199
|
entity |
| Predicate | readerImpact |
P95128
|
FINISHED |
| Object | elicitsSympathyForBothCharacters |
—
|
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: elicitsSympathyForBothCharacters | Statement: [Maggie Tulliver has a close relationship with Philip Wakem, readerImpact, elicitsSympathyForBothCharacters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: readerImpact Context triple: [Maggie Tulliver has a close relationship with Philip Wakem, readerImpact, elicitsSympathyForBothCharacters]
-
A.
effectOfPublication
Indicates the impact or consequence that a particular publication has on something, such as knowledge, behavior, policy, or subsequent events.
-
B.
readership
Indicates the relationship in which one party reads, follows, or is the audience for the written or published work of another.
-
C.
readerReception
chosen
Indicates how readers interpret, respond to, or are affected by a particular text or work.
-
D.
impactOnAuthor
Indicates that one entity has an effect, influence, or consequence on the author.
-
E.
impactOnSubject
Indicates the effect, influence, or consequence that one entity, event, or action has on a specified subject.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.