Triple
T19201691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Son of the Tree That Owns Itself |
E470122
|
entity |
| Predicate | plantedFrom |
P76746
|
FINISHED |
| Object | acorn of the original Tree That Owns Itself |
—
|
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: acorn of the original Tree That Owns Itself | Statement: [Son of the Tree That Owns Itself, plantedFrom, acorn of the original Tree That Owns Itself]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plantedFrom Context triple: [Son of the Tree That Owns Itself, plantedFrom, acorn of the original Tree That Owns Itself]
-
A.
plantedIn
Indicates that one entity has been placed or sown into another entity as its growing or containing medium.
-
B.
plantedAt
Indicates that one entity has been planted or placed into the ground or a specific location at or in association with another entity.
-
C.
plantedInYear
Indicates that something was planted or sown in a specific calendar year.
-
D.
plantSource
chosen
Indicates that something originates from, is derived from, or is produced by a particular plant.
-
E.
growsOn
Indicates that one entity develops or increases in size, number, or extent while being physically supported by or attached 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f9991ba48190ab92805daec3877b |
completed | April 20, 2026, 10:02 a.m. |
| PD | Predicate disambiguation | batch_69e4dcf22b3c8190bee02e3af946e114 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 12:07 p.m.