Triple
T32910145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Son of Dracula |
E841850
|
entity |
| Predicate | titleCharacterIs |
P138759
|
FINISHED |
| Object | vampire |
—
|
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: vampire | Statement: [Son of Dracula, titleCharacterIs, vampire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleCharacterIs Context triple: [Son of Dracula, titleCharacterIs, vampire]
-
A.
titleCharacterString
Indicates that one entity is the textual string representing the title associated with another entity.
-
B.
characterTitle
Indicates that a character holds or is associated with a specific title, rank, or formal designation.
-
C.
titleCharacterNamedAfter
Indicates that a work’s title character is named after, or shares their name with, another specific entity.
-
D.
titleCharacterState
Indicates the state or condition a character is in within the context of a specific title or work.
-
E.
titularCharacterOf
chosen
Indicates that one entity is the main or title character featured in the work represented by the other 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_69f34946a5208190bbd79f0fec4323bd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fee0b2da3c8190a3519d0564f2f32d |
completed | May 9, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69fee05b315c819081dfcbfb15273487 |
completed | May 9, 2026, 7:20 a.m. |
Created at: May 1, 2026, 1:19 a.m.