Triple
T18497573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tranquility |
E451987
|
entity |
| Predicate | containsSystem |
P58477
|
FINISHED |
| Object | life support systems |
—
|
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: life support systems | Statement: [Tranquility, containsSystem, life support systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsSystem Context triple: [Tranquility, containsSystem, life support systems]
-
A.
isInSystem
chosen
Indicates that one entity is located within, belongs to, or is contained by a particular system.
-
B.
hasBaseSystem
Indicates that one entity is founded upon, derived from, or primarily operates using another entity as its underlying system or framework.
-
C.
isPartOfSystemWithFeature
Indicates that one entity belongs to a system that possesses a specified feature or characteristic.
-
D.
hasPackageSystem
Indicates that an entity uses or is associated with a particular package management system for installing, updating, or managing software components.
-
E.
usesSameSystemAs
Indicates that two entities operate within or rely on the same underlying system, platform, or infrastructure.
- 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_69d8d3855d50819097fc8561b0299dd9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e532c15dec8190941e7c7a4cdebb66 |
completed | April 19, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69e469dbf5208190b6fc49e02a087f54 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:36 a.m.