Triple
T6554900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chesapeake Bay Bridge |
E152421
|
entity |
| Predicate | secondSpanOpened |
P71773
|
FINISHED |
| Object | 1973 |
—
|
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: 1973 | Statement: [Chesapeake Bay Bridge, secondSpanOpened, 1973]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondSpanOpened Context triple: [Chesapeake Bay Bridge, secondSpanOpened, 1973]
-
A.
firstSectionOpenedBetween
Indicates that the first section was opened at some point within a specified time interval or between two defined events.
-
B.
secondTunnelOpened
Indicates that a second tunnel has been opened and is now available for use in addition to an existing tunnel.
-
C.
openedSegment
Indicates that one entity has initiated or created a new segment, section, or interval within another entity or process.
-
D.
openedSectionBetween
Indicates that one entity has created or established an open section, gap, or interval between itself and another entity.
-
E.
secondHolder
Indicates that an entity is the second person or party to hold or possess a particular item, role, title, or position in a sequence.
- 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_69c688058d6881908c19b309cc55dbfa |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6c1b15d3481908ae66e3d7564b352 |
completed | March 27, 2026, 5:43 p.m. |
| PD | Predicate disambiguation | batch_69c6acf6d4148190914b19e9affd8c76 |
completed | March 27, 2026, 4:14 p.m. |
| PDg | Predicate description generation | batch_69c6c1b007148190b5164d6d09584cdf |
completed | March 27, 2026, 5:43 p.m. |
Created at: March 27, 2026, 1:51 p.m.