Triple
T13599282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddystone Rocks |
E324900
|
entity |
| Predicate | thirdLighthouseInnovation |
P32322
|
FINISHED |
| Object | interlocking stone blocks |
—
|
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: interlocking stone blocks | Statement: [Eddystone Rocks, thirdLighthouseInnovation, interlocking stone blocks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdLighthouseInnovation Context triple: [Eddystone Rocks, thirdLighthouseInnovation, interlocking stone blocks]
-
A.
innovationLevel
Indicates the degree or extent to which something is new, original, or creatively advanced compared to existing norms or solutions.
-
B.
innovationArea
Indicates the thematic or domain-specific field in which an innovation is focused or applied.
-
C.
hasInnovationType
Indicates that an entity is associated with, or classified by, a specific type or category of innovation.
-
D.
innovationFrom
chosen
Indicates that something originates, arises, or is derived as an innovation from a particular source or prior entity.
-
E.
portraysInnovation
Indicates that one entity depicts, represents, or conveys the idea of innovation in relation to another 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb0795acc8190a08667ab9dcb0d44 |
completed | April 12, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69dbae18eaf48190809e8b365856cde9 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:49 p.m.