Triple
T28184858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keyhole Route |
E716148
|
entity |
| Predicate | keyLandmark |
P22581
|
FINISHED |
| Object | The Keyhole |
—
|
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: The Keyhole | Statement: [Keyhole Route, keyLandmark, The Keyhole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyLandmark Context triple: [Keyhole Route, keyLandmark, The Keyhole]
-
A.
cityLandmarkID
Indicates that a specific landmark is uniquely identified as being located within a particular city.
-
B.
typeOfLandmark
Indicates the specific category or kind of landmark that an entity belongs to (e.g., monument, natural feature, building).
-
C.
includesLandmark
chosen
Indicates that one location or area contains or encompasses a specific landmark within its boundaries.
-
D.
primaryCityLandmarkOf
Indicates that a landmark is a principal or defining landmark associated with a specific city.
-
E.
notablePlace
Indicates that a place is especially significant, famous, or noteworthy in relation to the subject.
- 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_69efd6b4fc5c81909dd88f01a8c2b35d |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f64285d75481908da4a276fd8c4676 |
completed | May 2, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 10:22 p.m.