Triple
T28188326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KamLAND experiment |
E716234
|
entity |
| Predicate | firstDataTaking |
P195925
|
FINISHED |
| Object | 2002 |
—
|
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: 2002 | Statement: [KamLAND experiment, firstDataTaking, 2002]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstDataTaking Context triple: [KamLAND experiment, firstDataTaking, 2002]
-
A.
firstDataTakingYear
chosen
Indicates the year in which data was first collected or recorded for the given subject or context.
-
B.
firstTakenAt
Indicates the time or date at which something was initially taken, captured, or recorded for the first time.
-
C.
firstDataFromMars
Indicates that the referenced data instance is the earliest or initial data obtained from Mars.
-
D.
dataTakingEndDate
Indicates the date on which the process of collecting or taking data is completed or stops.
-
E.
firstObjectDiscovered
Indicates that the referenced object is the earliest one identified or detected in a given context or sequence.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69ffc516d1908190b475f5a6156b0ca8 |
completed | May 9, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69ffc4a946e08190b3535a5dc15ac484 |
completed | May 9, 2026, 11:35 p.m. |
Created at: April 27, 2026, 10:24 p.m.