Triple
T9287216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xiphodontidae |
E223422
|
entity |
| Predicate | skeletonPreservation |
P77563
|
FINISHED |
| Object | partial skeletons |
—
|
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: partial skeletons | Statement: [Xiphodontidae, skeletonPreservation, partial skeletons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skeletonPreservation Context triple: [Xiphodontidae, skeletonPreservation, partial skeletons]
-
A.
skeleton
Indicates that one entity serves as the basic structural framework or underlying support for another.
-
B.
fossilPreservation
chosen
Indicates that a fossil retains evidence of its original features or conditions through specific modes or quality of preservation.
-
C.
skeletonCoating
Indicates that one entity serves as a coating, covering, or outer layer on the skeleton of another entity.
-
D.
skeletonFeature
Indicates that one entity is a structural or anatomical skeletal feature or component of another entity.
-
E.
skeletonCompleteness
Indicates the degree to which an entity’s skeleton is present, intact, or fully preserved in relation to its expected complete form.
- 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_69ca8422ddf881908a3f8f876c9f53aa |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0861425c81909e3ab11e19cc2f65 |
completed | April 1, 2026, 11:58 a.m. |
| PD | Predicate disambiguation | batch_69cc7a576ec88190bbb787eb82e2e539 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:35 p.m.