Triple
T206461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moon |
E4619
|
entity |
| Predicate | formationHypothesis |
P119
|
FINISHED |
| Object | giant impact hypothesis |
—
|
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: giant impact hypothesis | Statement: [Moon, formationHypothesis, giant impact hypothesis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formationHypothesis Context triple: [Moon, formationHypothesis, giant impact hypothesis]
-
A.
formationPrinciple
Indicates the underlying rule, pattern, or principle according to which something is formed, structured, or brought into existence.
-
B.
formedBy
Indicates that something comes into existence or is created as a result of a specific agent, process, or combination of components.
-
C.
hasFormulation
Indicates that one entity is expressed, prepared, or configured in a particular form or composition defined by another entity.
-
D.
formationEvent
Indicates the event or process through which something comes into existence, is created, or is initially established.
-
E.
theorized
chosen
Indicates that one entity has proposed or developed a theoretical explanation or hypothesis about another entity or phenomenon.
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25e2aba74819093eddd8d820260c0 |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b4c7f908190876c1041db52dffc |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:51 a.m.