Triple
T9070638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | radiocarbon dating |
E217355
|
entity |
| Predicate | hasHalfLifeUsed |
P23051
|
FINISHED |
| Object | about 5730 years |
—
|
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: about 5730 years | Statement: [radiocarbon dating, hasHalfLifeUsed, about 5730 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHalfLifeUsed Context triple: [radiocarbon dating, hasHalfLifeUsed, about 5730 years]
-
A.
hasEliminationHalfLife
Indicates the duration required for half of a substance or entity to be removed, degraded, or rendered inactive within a given system or context.
-
B.
hasPartUsed
Indicates that an entity utilizes another entity as a component or constituent part in its structure, function, or operation.
-
C.
hasMeanLifetime
chosen
Indicates the characteristic average time duration for which an entity, state, or condition persists before it decays, ends, or changes.
-
D.
hasHumanUse
Indicates that something is used, employed, or utilized by humans for a particular purpose or benefit.
-
E.
hasPartiallyLostUseOf
Indicates that an entity has experienced a reduction, but not a complete loss, in the functional use of another entity.
- 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc955d29548190a204efd3257b6d5d |
completed | April 1, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69cc65f881248190bfd220bb28a9fb5f |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:11 p.m.