Triple
T1617923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marquette Harbor Lighthouse |
E34761
|
entity |
| Predicate | towerAttachment |
P30478
|
FINISHED |
| Object | attached to keeper’s dwelling |
—
|
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: attached to keeper’s dwelling | Statement: [Marquette Harbor Lighthouse, towerAttachment, attached to keeper’s dwelling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: towerAttachment Context triple: [Marquette Harbor Lighthouse, towerAttachment, attached to keeper’s dwelling]
-
A.
towerName
Indicates the specific name assigned to a tower in the relationship.
-
B.
towerType
Indicates the specific kind or classification of a tower that an entity is associated with or represents.
-
C.
towerShape
Indicates that one entity has the physical form or outline of a tower in relation to another entity.
-
D.
tallestBuildingIn
Indicates that one entity is the tallest building located within the area or region specified by the other entity.
-
E.
towerInclination
Indicates the degree and direction to which a tower deviates or leans away from a perfectly vertical alignment.
- F. None of above. chosen
Provenance (4 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_69a885ffc5ec819091afa325d5f9611c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fef600c819080fe75c42c8e6dac |
completed | March 5, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69a907c52a548190b648a31ea306dd5b |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a93fedcb108190ad91f938d5eeaaa2 |
completed | March 5, 2026, 8:33 a.m. |
Created at: March 4, 2026, 7:28 p.m.