Triple
T26592940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allan Willis |
E667408
|
entity |
| Predicate | hasRelativeInStory |
P86993
|
FINISHED |
| Object | Tom Willis |
—
|
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: Tom Willis | Statement: [Allan Willis, hasRelativeInStory, Tom Willis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRelativeInStory Context triple: [Allan Willis, hasRelativeInStory, Tom Willis]
-
A.
hasSiblingInStory
Indicates that one character in a narrative has at least one sibling who also appears within the same story.
-
B.
hasTimeInStory
Indicates that a story element, event, or entity occurs or is present during a specific time or time interval within the narrative.
-
C.
storylineRelative
Indicates that one narrative element is positioned in relation to another within a storyline, such as in sequence, importance, or structural role.
-
D.
hasRelativeInFiction
chosen
Indicates that one entity has a relative or family member who appears as a character within a fictional work associated with the other entity.
-
E.
hasAllyInStory
Indicates that one entity is portrayed as an ally or supportive partner of another entity within the context of a specific story or narrative.
- 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_69ee9cfc385081909ac9ae178030a06e |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69fddd373cdc8190be1b12e70e4deb1f |
completed | May 8, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_69fddc6915a88190ad41e379aa3ede13 |
completed | May 8, 2026, 12:51 p.m. |
Created at: April 27, 2026, 2:09 a.m.