Triple
T34494448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madelyn Stillwell |
E885559
|
entity |
| Predicate | romanticDynamicWith |
P140327
|
FINISHED |
| Object | Homelander |
—
|
NE NERFINISHED |
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: Homelander | Statement: [Madelyn Stillwell, romanticDynamicWith, Homelander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanticDynamicWith Context triple: [Madelyn Stillwell, romanticDynamicWith, Homelander]
-
A.
romanticPattern
Indicates a recurring style, tendency, or structure in how romantic relationships or attractions develop or are expressed between entities.
-
B.
romanticFeeling
chosen
Indicates that one entity experiences romantic attraction or affection toward another entity.
-
C.
romanticSceneWith
Indicates a scene or situation in which the two entities are engaged together in a romantic context or interaction.
-
D.
romanticRivalryWith
Indicates a mutual competitive relationship in which two entities vie for the romantic attention or affection of the same person.
-
E.
romanticOutcome
Indicates that a romantic relationship or interaction between entities results in a particular outcome, such as success, failure, or change in status.
- 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_69f349cafcec8190997b45b3fdc16c27 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7817daf00819098936402e75ab0a6 |
completed | May 3, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f780fc5ed88190b7200ee5a29940af |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 1, 2026, 2:01 a.m.