Triple
T4790913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorcas |
E106597
|
entity |
| Predicate | memoryAfterDeath |
P15970
|
FINISHED |
| Object | haunts surviving characters |
—
|
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: haunts surviving characters | Statement: [Dorcas, memoryAfterDeath, haunts surviving characters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryAfterDeath Context triple: [Dorcas, memoryAfterDeath, haunts surviving characters]
-
A.
deathBefore
Indicates that one entity’s death occurred earlier in time than another entity’s death.
-
B.
memory
chosen
Indicates that an entity retains, recalls, or is associated with stored information or past experiences.
-
C.
associatedAfterlife
Indicates a relationship where an entity is linked to, or characterized by, a particular concept, realm, or state of existence after death.
-
D.
containsDeathOf
Indicates that the subject includes, depicts, or involves the death of the referenced entity.
-
E.
endedActivityAfterDeathOf
Indicates that an activity was terminated following, and as a consequence of, the death of a specified 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_69bd43f591c881909e5a532388b0f3f3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd65ddff388190b55071ed5cae7688 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd622e1b408190806c15c61519fc74 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:22 p.m.