Triple
T33380527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Megapodius cumingii |
E854760
|
entity |
| Predicate | clutchCharacteristic |
P128001
|
FINISHED |
| Object | large eggs relative to body size |
—
|
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 eggs relative to body size | Statement: [Megapodius cumingii, clutchCharacteristic, large eggs relative to body size]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clutchCharacteristic Context triple: [Megapodius cumingii, clutchCharacteristic, large eggs relative to body size]
-
A.
clutchType
Indicates the type or category of clutch mechanism associated with or used by an entity.
-
B.
clutchOperation
Indicates the action or process of engaging or disengaging a clutch mechanism to transmit or interrupt power between connected components.
-
C.
entityCharacteristic
chosen
Indicates that an entity possesses, exhibits, or is defined by a particular characteristic or attribute.
-
D.
clutchPlacement
Indicates the spatial or positional arrangement of a clutch (e.g., eggs or offspring) relative to a reference object, location, or parent.
-
E.
dataCharacteristic
Indicates that one entity specifies a property, attribute, or feature that characterizes a given piece of data.
- 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_69f3496ca10c8190908640d18fa00832 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e00147d48190880fdcb31be37dcc |
completed | May 3, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69f6de0c821c8190ae3ebda9dfdd0064 |
completed | May 3, 2026, 5:33 a.m. |
Created at: May 1, 2026, 1:35 a.m.