Triple
T17977285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dylan Harper |
E449507
|
entity |
| Predicate | relationshipEvolvesTo |
P87667
|
FINISHED |
| Object | romantic relationship |
—
|
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: romantic relationship | Statement: [Dylan Harper, relationshipEvolvesTo, romantic relationship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipEvolvesTo Context triple: [Dylan Harper, relationshipEvolvesTo, romantic relationship]
-
A.
relationshipDevelopsWith
chosen
Indicates that a relationship grows, evolves, or becomes more developed between two entities over time.
-
B.
relationshipDynamic
Indicates a changing or evolving pattern of interaction between entities, such as shifts in their roles, closeness, or influence over time.
-
C.
relationshipOutcome
Indicates the result or consequence that arises from a particular relationship between two or more entities.
-
D.
laterRelationshipWith
Indicates that one entity has a relationship with another that occurs at a later time relative to some reference point or prior relationship.
-
E.
relationshipImpact
Indicates how one entity’s relationship with another affects or changes those entities or their interaction.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b20010c8819088c022565183a7ff |
completed | April 19, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:22 a.m.