Triple
T7722617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Space Shuttle thermal protection system |
E175049
|
entity |
| Predicate | tileCount |
P78787
|
FINISHED |
| Object | approximately 24,000 tiles |
—
|
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: approximately 24,000 tiles | Statement: [Space Shuttle thermal protection system, tileCount, approximately 24,000 tiles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tileCount Context triple: [Space Shuttle thermal protection system, tileCount, approximately 24,000 tiles]
-
A.
tierCount
Indicates the number of distinct levels, ranks, or layers associated with an entity in a hierarchical or tiered structure.
-
B.
pixelCount
Indicates the total number of individual pixels that make up a given image or visual element.
-
C.
titleCount
Indicates the number of distinct titles associated with an entity within a given context.
-
D.
ballCount
Indicates the number of balls associated with a given entity or context.
-
E.
roofCount
Indicates the number of distinct roofs associated with an entity (such as a building or structure).
- F. None of above. chosen
Provenance (4 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
| PDg | Predicate description generation | batch_69c7074cd1f081908d5e8951660e7271 |
completed | March 27, 2026, 10:40 p.m. |
Created at: March 27, 2026, 4:05 p.m.