Triple
T14107358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elephant’s Child |
E339540
|
entity |
| Predicate | causeOfLongTrunk |
P20829
|
FINISHED |
| Object | crocodile pulling his nose |
—
|
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: crocodile pulling his nose | Statement: [Elephant’s Child, causeOfLongTrunk, crocodile pulling his nose]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causeOfLongTrunk Context triple: [Elephant’s Child, causeOfLongTrunk, crocodile pulling his nose]
-
A.
numberOfTrunksApprox
Indicates an approximate count of trunks associated with an entity, rather than an exact number.
-
B.
longType
Indicates that something has a length-related classification or is characterized by being of extended duration or distance.
-
C.
circuitHasLongStraight
Indicates that a circuit includes at least one long, uninterrupted straight section.
-
D.
isElongatedDueTo
chosen
Indicates that one entity becomes longer in shape, form, or duration specifically as a result of the influence or effect of another entity or factor.
-
E.
maximumTrunkDiameter
Indicates the largest thickness of a trunk measured across its widest point.
- 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_69d81c69b5c8819094aa1abf18302908 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de600ada808190b92d67dc30f13d15 |
completed | April 14, 2026, 3:40 p.m. |
| PD | Predicate disambiguation | batch_69de05b2f7e481908a9a7d40153234c0 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:22 p.m.