Triple
T28605477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dark Tower series |
E724033
|
entity |
| Predicate | hasCharacterAlias |
P117206
|
FINISHED |
| Object | John |
—
|
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: John | Statement: [The Dark Tower series, hasCharacterAlias, John]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCharacterAlias Context triple: [The Dark Tower series, hasCharacterAlias, John]
-
A.
associatedWithCharacterAlias
Indicates that one entity is linked to or connected with an alternative name or alias used for a particular character.
-
B.
hasTitleCharacterAlias
chosen
Indicates that a title (such as a work or publication) is associated with an alternate or alias name for one of its characters.
-
C.
characterAlias
Indicates that one character is known or referred to by an alternative name or alias.
-
D.
hasFictionalAlias
Indicates that an entity is known by an alternative name or identity within a fictional context.
-
E.
hasCharacterNamedAfter
Indicates that one entity has a character whose name is derived from or intentionally based on 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 28, 2026, 4:27 a.m.