Triple
T1464045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isle of May |
E31577
|
entity |
| Predicate | hasOldestLighthouse |
P18087
|
FINISHED |
| Object | one of Scotland’s earliest lighthouses |
—
|
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: one of Scotland’s earliest lighthouses | Statement: [Isle of May, hasOldestLighthouse, one of Scotland’s earliest lighthouses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOldestLighthouse Context triple: [Isle of May, hasOldestLighthouse, one of Scotland’s earliest lighthouses]
-
A.
isOldest
Indicates that one entity has a greater age than all other relevant entities in the comparison set.
-
B.
oldestKnownFeature
Indicates that the related feature is the earliest or most ancient one known within a given context or set.
-
C.
oldestStandingStructureIn
chosen
Indicates that one entity is the oldest still-existing structure located within the specified place or region.
-
D.
lighthouseRebuilt
Indicates that a lighthouse, previously existing, has been reconstructed or built again after damage, destruction, or decommissioning.
-
E.
isOldestOrderOf
Indicates that one order is the earliest or first created among a set of related orders for a given context or 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_69a49917dfc081909acdbdf5d684f1ef |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c5b89708819084fb9ba4ff293b8b |
completed | March 1, 2026, 11:03 p.m. |
| PD | Predicate disambiguation | batch_69a4c48121e48190946c23c583e5fb64 |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8 p.m.