Triple
T29431015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard |
E746431
|
entity |
| Predicate | sharesNarrativeWith |
P86750
|
FINISHED |
| Object | Marina |
—
|
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: Marina | Statement: [Howard, sharesNarrativeWith, Marina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesNarrativeWith Context triple: [Howard, sharesNarrativeWith, Marina]
-
A.
sharesStoryElementsWith
chosen
Indicates that two narratives or works have overlapping or similar plot points, themes, characters, or other storytelling components.
-
B.
sharesTimelineWith
Indicates that two entities participate in or are associated with the same timeline, sequence of events, or temporal context.
-
C.
sharesProtagonistWith
Indicates that two narrative works feature the same main protagonist character.
-
D.
narratesWith
Indicates that one entity tells, recounts, or presents a story, event, or information in conjunction with or alongside another entity.
-
E.
sharesFeatureWith
Indicates that two entities have at least one common attribute, property, or characteristic in common.
- 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_69f0a7a06e0081908add494075912eb4 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fde49a084081909d99b1e0258169d5 |
completed | May 8, 2026, 1:26 p.m. |
| PD | Predicate disambiguation | batch_69fde1d04bd881909a46ecbbf18dfe59 |
completed | May 8, 2026, 1:14 p.m. |
Created at: April 28, 2026, 3:13 p.m.