Triple
T25006523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lilim |
E625854
|
entity |
| Predicate | takesForm |
P90593
|
FINISHED |
| Object | human form |
—
|
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: human form | Statement: [The Lilim, takesForm, human form]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: takesForm Context triple: [The Lilim, takesForm, human form]
-
A.
usesForm
Indicates that one entity employs, applies, or operates through a particular form, format, or structured representation of something.
-
B.
canTakeForm
chosen
Indicates that one entity is capable of assuming, transforming into, or being represented as the form or appearance of another entity.
-
C.
nativeForm
Indicates that one entity is the original or native linguistic form of another, such as a word’s form in its source language.
-
D.
containsForm
Indicates that one entity includes or encapsulates another entity as a form, structure, or representation within it.
-
E.
typicalForm
Indicates that one entity represents the standard, characteristic, or most common form or shape in which another entity typically appears or is realized.
- 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_69e2ff26c50481908bc82e799c9e6587 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f44b113f8c8190ae05102e9c2ae076 |
completed | May 1, 2026, 6:41 a.m. |
| PD | Predicate disambiguation | batch_69f442c0c2e88190acd7f170f10ccef6 |
completed | May 1, 2026, 6:05 a.m. |
Created at: April 18, 2026, 6:05 a.m.