Triple
T11525726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seoullo 7017 |
E273288
|
entity |
| Predicate | safetyUpgradeFrom |
P37414
|
FINISHED |
| Object | aging elevated roadway |
—
|
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: aging elevated roadway | Statement: [Seoullo 7017, safetyUpgradeFrom, aging elevated roadway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safetyUpgradeFrom Context triple: [Seoullo 7017, safetyUpgradeFrom, aging elevated roadway]
-
A.
upgradesFrom
chosen
Indicates that one entity is a newer or improved version that replaces or enhances another entity.
-
B.
upgradeOf
Indicates that one entity is a newer, improved, or more advanced version of another entity.
-
C.
upgradeType
Indicates the specific kind or category of improvement or enhancement applied to an entity relative to its previous state.
-
D.
wasUpgradedFor
Indicates that one entity was improved, enhanced, or updated specifically to serve, benefit, or be compatible with another entity.
-
E.
upgradedBy
Indicates that an entity has been improved, enhanced, or moved to a higher version or level as a result of actions performed by 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_69d6aae3fbec8190a14632a5df2538b6 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d87fd379648190b342e0c4b4f685b7 |
completed | April 10, 2026, 4:42 a.m. |
| PD | Predicate disambiguation | batch_69d80879fdb48190be6dacc8aa63c809 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.