Triple
T37452583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torvosaurus |
E930706
|
entity |
| Predicate | skullOrientation |
P117695
|
FINISHED |
| Object | deep and narrow skull |
—
|
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: deep and narrow skull | Statement: [Torvosaurus, skullOrientation, deep and narrow skull]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skullOrientation Context triple: [Torvosaurus, skullOrientation, deep and narrow skull]
-
A.
skullMorphology
chosen
Indicates a relationship where entities are characterized or compared based on the form, structure, or anatomical features of their skulls.
-
B.
coneOrientation
Indicates the directional alignment or pointing direction of a cone relative to a reference frame or object.
-
C.
skullUsage
Indicates how a skull is used, applied, or functionally involved in a particular context or activity.
-
D.
functionalOrientation
Indicates a relationship where an entity is characterized by the specific function, role, or operational purpose it is oriented or designed to fulfill.
-
E.
skullOrnamentation
Indicates that an entity has decorative or structural features specifically adorning or modifying the skull.
- 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_69f76ec0b9488190b7a4fae632bd1d2f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb92efc5948190a040ba2028bab964 |
completed | May 6, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0b52588190bb29937a43b99b5e |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:17 p.m.