Triple
T32467673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cistern Spring |
E829754
|
entity |
| Predicate | refillsAfter |
P174208
|
FINISHED |
| Object | Steamboat Geyser eruption sequence subsides |
—
|
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: Steamboat Geyser eruption sequence subsides | Statement: [Cistern Spring, refillsAfter, Steamboat Geyser eruption sequence subsides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refillsAfter Context triple: [Cistern Spring, refillsAfter, Steamboat Geyser eruption sequence subsides]
-
A.
replenishment
Indicates the action or process of refilling or restoring a resource, supply, or quantity to a desired or original level.
-
B.
numberOfRefuelings
Indicates the count of times a refueling event occurs for a given entity or process.
-
C.
refueledAt
Indicates that an entity replenished its fuel supply at a specified location or facility.
-
D.
boosterReuseCountAtLaunch
Indicates the number of times a booster has been previously reused at the moment of this launch.
-
E.
reconfirmedAfter
Indicates that something has been confirmed again at a later time following an earlier confirmation.
- 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_69f3491ee87c81908cbf5890079c2af6 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c3532914819092d6de99dea68578 |
completed | May 3, 2026, 3:38 a.m. |
| PD | Predicate disambiguation | batch_69f6ba700a708190ab6db62791e43774 |
completed | May 3, 2026, 3:01 a.m. |
| PDg | Predicate description generation | batch_69f6bbbe23d48190b2aa662d69b41900 |
completed | May 3, 2026, 3:06 a.m. |
Created at: May 1, 2026, 12:57 a.m.