Triple
T27351604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qi Great Wall ruins |
E684372
|
entity |
| Predicate | endConstructionTime |
P162214
|
FINISHED |
| Object | 3rd century BCE |
—
|
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: 3rd century BCE | Statement: [Qi Great Wall ruins, endConstructionTime, 3rd century BCE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endConstructionTime Context triple: [Qi Great Wall ruins, endConstructionTime, 3rd century BCE]
-
A.
constructionTime
Indicates the duration or specific point in time required to construct or build an entity.
-
B.
startOfConstructionApprox
Indicates that the construction of something began around an approximate or estimated point in time, rather than on a precisely known date.
-
C.
timeToComplete
Indicates the duration required for an entity or process to be fully completed.
-
D.
hasEndConstruction
Indicates that an entity is associated with, or terminates in, a specific construction or structural element at its end.
-
E.
typicalConstructionEnd
Indicates the usual or expected point in time or stage at which a construction process or building project is completed.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62ba8515881908899834ffc730a6e |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69f621fbfc2c8190bfa802d7dc0f6aa4 |
completed | May 2, 2026, 4:10 p.m. |
Created at: April 27, 2026, 11:49 a.m.