Triple
T32948799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benjamin |
E842881
|
entity |
| Predicate | featuresRomanticRelationshipBetween |
P121646
|
FINISHED |
| Object | Benjamin and Noah |
—
|
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: Benjamin and Noah | Statement: [Benjamin, featuresRomanticRelationshipBetween, Benjamin and Noah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresRomanticRelationshipBetween Context triple: [Benjamin, featuresRomanticRelationshipBetween, Benjamin and Noah]
-
A.
exploresRomanticRelationships
Indicates that one entity engages in or investigates romantic relationships with another entity.
-
B.
featuresSameSexRelationship
Indicates that the subject includes or portrays a romantic or sexual relationship between individuals of the same sex.
-
C.
romanticAssociation
chosen
Indicates a romantic relationship or involvement exists between the associated entities.
-
D.
romanceType
Indicates the specific kind or category of romantic relationship that exists between the related entities.
-
E.
romanticFeeling
Indicates that one entity experiences romantic attraction or affection toward another 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_69f3494a31f481909057136e49b4fe60 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a0144c75aec81908bdd9e88f2af737a |
completed | May 11, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_6a014405a2d48190a1d58b0b907ad696 |
completed | May 11, 2026, 2:50 a.m. |
Created at: May 1, 2026, 1:21 a.m.