Triple
T12783691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onychoprion |
E305569
|
entity |
| Predicate | colonialSize |
P52485
|
FINISHED |
| Object | large breeding colonies |
—
|
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: large breeding colonies | Statement: [Onychoprion, colonialSize, large breeding colonies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colonialSize Context triple: [Onychoprion, colonialSize, large breeding colonies]
-
A.
colonySize
chosen
Indicates the number of individuals or units that make up a colony in the described context.
-
B.
numberOfColonies
Indicates the count of distinct colonies associated with or possessed by a given entity.
-
C.
colonyOf
Indicates that one entity is a colony belonging to, founded by, or politically dependent on another entity.
-
D.
representedColony
Indicates that an entity acted as an official representative or delegate for a particular colony in some context or event.
-
E.
colonialDesignation
Indicates that one entity assigns or holds a status, name, or classification for another entity within a colonial or colonially imposed framework.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e5cb3c08190b8e1e22de8b96e17 |
completed | April 10, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69d9640ba0688190973e4e7ec8d4a8e0 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:29 p.m.