Triple
T149406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portcullis with chains |
E3398
|
entity |
| Predicate | visualAssociation |
P2830
|
FINISHED |
| Object | entrance to a fortified 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: entrance to a fortified castle | Statement: [Portcullis with chains, visualAssociation, entrance to a fortified castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualAssociation Context triple: [Portcullis with chains, visualAssociation, entrance to a fortified castle]
-
A.
vision
Indicates that an entity perceives another entity or object visually, using sight.
-
B.
isAssociatedWith
chosen
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
-
C.
notablyAssociatedWith
Indicates that one entity is prominently or distinctively connected with another in a way that is especially noteworthy or remarkable.
-
D.
symbolizes
Indicates that one entity stands for, represents, or is used as a sign for another entity, concept, or idea.
-
E.
captures
Indicates that one entity seizes, traps, or takes control of another entity, often preventing its escape or freedom.
- 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_69a252868de4819080e21c9938bfe8b6 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a2580ca15481909fa3e87d804a1b23 |
completed | Feb. 28, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69a256599db08190a7b000b381d32ec4 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.