Triple
T9936547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddie Kaspbrak |
E192772
|
entity |
| Predicate | parallel |
P91241
|
FINISHED |
| Object | Myra Kaspbrak resembles Sonia Kaspbrak in behavior |
—
|
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: Myra Kaspbrak resembles Sonia Kaspbrak in behavior | Statement: [Eddie Kaspbrak, parallel, Myra Kaspbrak resembles Sonia Kaspbrak in behavior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parallel Context triple: [Eddie Kaspbrak, parallel, Myra Kaspbrak resembles Sonia Kaspbrak in behavior]
-
A.
parallelPassage
Indicates that one text segment corresponds closely in content or structure to another, such that they can be considered parallel versions or accounts of the same material.
-
B.
par
Indicates that two entities are parallel to each other in space or direction.
-
C.
parallelEvent
Indicates that two or more events occur at the same time or overlap in time without a required order between them.
-
D.
parallelPosition
Indicates that two entities occupy positions that are aligned in parallel relative to a reference frame or axis.
-
E.
parity
Indicates that two quantities share the same evenness or oddness, or more generally that they have equivalent status or value in a given context.
- F. None of above. chosen
Provenance (4 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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9428cc81909b4b4938566d78a7 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd358386f48190833c862b5b8c04b2 |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:44 p.m.