Triple
T37344183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weirton Steel Corporation |
E927126
|
entity |
| Predicate | economyOfTopic |
P188305
|
FINISHED |
| Object | Weirton, West Virginia |
—
|
NE NERFINISHED |
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: Weirton, West Virginia | Statement: [Weirton Steel Corporation, economyOfTopic, Weirton, West Virginia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: economyOfTopic Context triple: [Weirton Steel Corporation, economyOfTopic, Weirton, West Virginia]
-
A.
economicSpeciality
Indicates a relationship where an entity is characterized by, or primarily engaged in, a particular economic field, sector, or type of economic activity.
-
B.
economicScope
Indicates the range or extent of economic activities, impacts, or considerations that a given entity, action, or relationship encompasses.
-
C.
economyIncludes
Indicates that an economy encompasses, contains, or is composed of the specified component, sector, or element.
-
D.
economicTrend
Indicates the general direction or pattern of economic activity or conditions over a period of time.
-
E.
economyContrast
Indicates that two entities are being compared or opposed in terms of their economic characteristics, conditions, or performance.
- 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_69f76eb5e034819088e53ab5b7909a68 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba68077788190b311e027435fcf87 |
completed | May 6, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fba34c65ac8190b298f0f00d1dcc0e |
completed | May 6, 2026, 8:23 p.m. |
| PDg | Predicate description generation | batch_69fba67f78348190ab160988e4698394 |
completed | May 6, 2026, 8:37 p.m. |
Created at: May 3, 2026, 4:16 p.m.