Triple
T27826370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rostral Columns with ship prows |
E702962
|
entity |
| Predicate | lightingOccasion |
P163729
|
FINISHED |
| Object | city celebrations |
—
|
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: city celebrations | Statement: [Rostral Columns with ship prows, lightingOccasion, city celebrations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lightingOccasion Context triple: [Rostral Columns with ship prows, lightingOccasion, city celebrations]
-
A.
displayOccasion
Indicates the event, context, or situation during which something is presented, shown, or made visible.
-
B.
targetOccasion
Indicates the specific event, situation, or occasion toward which an action, plan, or intention is directed.
-
C.
suitableOccasion
Indicates that a particular occasion or context is appropriate or fitting for a given entity, action, or event.
-
D.
entryOccasion
Indicates the circumstance, event, or reason that prompts or justifies an entity’s entry or initiation.
-
E.
premiereOccasion
Indicates the event or context in which something (such as a work, show, or product) is first publicly presented or launched.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63c045bd081908e0cb2a119202e8f |
completed | May 2, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63b3039808190b00bbd19161487f3 |
completed | May 2, 2026, 5:58 p.m. |
Created at: April 27, 2026, 5:52 p.m.