Triple
T37787636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baku–Tbilisi–Ceyhan pipeline |
E941995
|
entity |
| Predicate | connectedField |
P199794
|
FINISHED |
| Object | Azeri–Chirag–Gunashli oil field |
—
|
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: Azeri–Chirag–Gunashli oil field | Statement: [Baku–Tbilisi–Ceyhan pipeline, connectedField, Azeri–Chirag–Gunashli oil field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectedField Context triple: [Baku–Tbilisi–Ceyhan pipeline, connectedField, Azeri–Chirag–Gunashli oil field]
-
A.
connectedToField
chosen
Indicates that one entity has a direct link, association, or attachment to a specific field within a structure, system, or dataset.
-
B.
relatedField
Indicates that one field, topic, or area of study is connected or relevant to another in subject matter or application.
-
C.
connectedLine
Indicates that two entities are joined by a continuous line or linear connection.
-
D.
commonField
Indicates that two or more entities share at least one field, attribute, or data element in common.
-
E.
plannedToBeConnectedTo
Indicates that one entity is intended or scheduled to be linked or joined with another entity in the future.
- 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a00037bf4148190a58593d30efdd3f8 |
completed | May 10, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_6a0000b7af608190b718fc4111bcdad8 |
completed | May 10, 2026, 3:51 a.m. |
Created at: May 3, 2026, 4:19 p.m.