Triple
T25180519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grimes Graves |
E630569
|
entity |
| Predicate | publiclyAccessibleShaftName |
P160902
|
FINISHED |
| Object | Pit 1 |
—
|
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: Pit 1 | Statement: [Grimes Graves, publiclyAccessibleShaftName, Pit 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publiclyAccessibleShaftName Context triple: [Grimes Graves, publiclyAccessibleShaftName, Pit 1]
-
A.
hasPubliclyAccessibleShaft
chosen
Indicates that an entity possesses a shaft (such as a tunnel, elevator, or similar vertical/horizontal passage) that is accessible for use or entry by the general public.
-
B.
hasPrimaryAccessShaft
Indicates that one entity serves as the main access shaft associated with another entity.
-
C.
typicalShaftType
Indicates the usual or characteristic type of shaft associated with an entity or configuration.
-
D.
hasShafts
Indicates that one entity possesses or is equipped with one or more shafts as components or structural elements.
-
E.
shaftFeature
Indicates a relationship where one object possesses or is characterized by a shaft-like structural feature.
- 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_69e75a88fdf081908e47ae6e195c14e1 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 21, 2026, 12:35 p.m.