Triple
T19876203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karin Kinsella |
E477642
|
entity |
| Predicate | speaksLine |
P84993
|
FINISHED |
| Object | People will come, Ray. |
—
|
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: People will come, Ray. | Statement: [Karin Kinsella, speaksLine, People will come, Ray.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speaksLine Context triple: [Karin Kinsella, speaksLine, People will come, Ray.]
-
A.
dialogueLine
Indicates that one entity is a specific spoken or written line of dialogue expressed by another entity (such as a character or speaker).
-
B.
speaksWith
Indicates that one entity engages in spoken communication or conversation with another entity.
-
C.
spokenAlong
Indicates that two or more languages are used concurrently or within the same context in a particular place, time, or situation.
-
D.
famousLineSpeaker
chosen
Indicates that the subject is the person who spoke or delivered the famous line referenced by the object.
-
E.
givesSpeechTo
Indicates that one entity delivers a speech or formal address directed toward another entity or audience.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658db058c8190b7bf0b003ead5bfc |
completed | April 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69e537e8c4e481909fe95d795b4864e7 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.