Triple
T1037802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starliner spacecraft |
E22403
|
entity |
| Predicate | heatShield |
P14978
|
FINISHED |
| Object | ablative heat shield |
—
|
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: ablative heat shield | Statement: [Starliner spacecraft, heatShield, ablative heat shield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heatShield Context triple: [Starliner spacecraft, heatShield, ablative heat shield]
-
A.
heatShieldType
chosen
Indicates the specific kind or category of heat shield associated with an object or system.
-
B.
featuresShield
Indicates that an entity includes or is equipped with a shield as one of its characteristics or components.
-
C.
designedToWithstand
Indicates that something has been intentionally created or engineered to resist, endure, or remain functional under specified conditions, forces, or stresses.
-
D.
operatingTemperature
Indicates the range or specific value of temperature within which an entity is designed or allowed to function properly.
-
E.
shieldColor
Indicates the color attribute assigned to a shield in the relationship.
- 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_69a493d91478819094cc01fb65564bc1 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b97c64a88190bf1119fdd4940bf3 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b729f8488190b2042bd9c625a833 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.