Triple
T494845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Castle of Otranto |
E10269
|
entity |
| Predicate | containsMotif |
P8151
|
FINISHED |
| Object | haunted castle |
—
|
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: haunted castle | Statement: [The Castle of Otranto, containsMotif, haunted castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsMotif Context triple: [The Castle of Otranto, containsMotif, haunted castle]
-
A.
containsText
Indicates that one entity includes the specified text string within its content.
-
B.
containsMostOf
Indicates that one entity includes the majority (but not necessarily all) of the substance, elements, or components of another entity.
-
C.
containsCharacter
Indicates that one entity includes a specific character as part of its content or composition.
-
D.
primaryMotif
Indicates that one entity serves as the main recurring theme or dominant motif associated with another entity.
-
E.
hasPattern
chosen
Indicates that one entity exhibits, follows, or is characterized by a specific recurring form, structure, or design defined by 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_69a2e847df8481909239ec08ccf1e376 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f0fdd5608190815fa36485df8962 |
completed | Feb. 28, 2026, 1:43 p.m. |
| PD | Predicate disambiguation | batch_69a2edf90ca88190b6a182e5b6733612 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.