Triple
T1247227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary’s Well |
E26794
|
entity |
| Predicate | usedHistoricallyFor |
P2417
|
FINISHED |
| Object | drawing drinking water |
—
|
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: drawing drinking water | Statement: [Mary’s Well, usedHistoricallyFor, drawing drinking water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedHistoricallyFor Context triple: [Mary’s Well, usedHistoricallyFor, drawing drinking water]
-
A.
historicallyUsedFor
chosen
Indicates that something served a particular function or purpose at some point in the past, even if it may no longer be used that way now.
-
B.
historicUsePersistsIn
Indicates that a practice, feature, or condition originating in the past continues to exist or be applied in the present.
-
C.
usedAt
Indicates that something is employed, applied, or utilized at a particular place, time, or context.
-
D.
usedToBe
Indicates that something held a particular state, role, or property in the past but no longer does in the present.
-
E.
hasHumanUse
Indicates that something is used, employed, or utilized by humans for a particular purpose or benefit.
- 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_69a4948689d08190b3a4a3f388c02148 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf6750a48190b86e9248ed54d90a |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6b075881908e867c25b5080e25 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.