Triple
T17232418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Harris |
E418273
|
entity |
| Predicate | romanticTragedy |
P126482
|
FINISHED |
| Object | dies at the hands of Edward Hyde |
—
|
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: dies at the hands of Edward Hyde | Statement: [Lucy Harris, romanticTragedy, dies at the hands of Edward Hyde]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanticTragedy Context triple: [Lucy Harris, romanticTragedy, dies at the hands of Edward Hyde]
-
A.
romanticArc
Indicates a developing or ongoing romantic relationship or storyline between the involved entities.
-
B.
romanticallyObsessedWith
Indicates a strong, often overwhelming romantic fixation or preoccupation that one entity has toward another.
-
C.
romanticOutcome
Indicates that a romantic relationship or interaction between entities results in a particular outcome, such as success, failure, or change in status.
-
D.
romanticPattern
Indicates a recurring style, tendency, or structure in how romantic relationships or attractions develop or are expressed between entities.
-
E.
romanticRivalryWith
Indicates a mutual competitive relationship in which two entities vie for the romantic attention or affection of the same person.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42df7da748190a3a1762a67eb871b |
completed | April 19, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69e3832553ac819091aa917c84f755b6 |
completed | April 18, 2026, 1:12 p.m. |
| PDg | Predicate description generation | batch_69e3873f62108190966c4e741ebd548d |
completed | April 18, 2026, 1:29 p.m. |
Created at: April 10, 2026, 5:39 a.m.