Triple
T36482812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Launch Complex 34 |
E898861
|
entity |
| Predicate | hasNearbyComplex |
P118122
|
FINISHED |
| Object | Launch Complex 37 |
—
|
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: Launch Complex 37 | Statement: [Launch Complex 34, hasNearbyComplex, Launch Complex 37]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyComplex Context triple: [Launch Complex 34, hasNearbyComplex, Launch Complex 37]
-
A.
hasNearbyFunction
Indicates that one entity has another entity located close by that serves a related or supportive function.
-
B.
hasNearbyConfluenceWith
Indicates that one geographic feature, typically a waterway, is located close to the point where another waterway joins or merges with it.
-
C.
hasNearbyPoint
chosen
Indicates that one entity has at least one other point located within a specified proximity or distance from it.
-
D.
hasNearbyCommon
Indicates that two entities share at least one common element, feature, or connection that is located within a specified nearby distance or vicinity.
-
E.
hasNearbyEntityType
Indicates that an entity has at least one other entity of a specified type located within a defined nearby spatial or contextual range.
- 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_69f76e5a0e088190a2b6706aeb41723c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a005be4615c8190a710ab704a46c564 |
completed | May 10, 2026, 10:20 a.m. |
| PD | Predicate disambiguation | batch_6a005b8b1cc08190850a392761b84e74 |
completed | May 10, 2026, 10:18 a.m. |
Created at: May 3, 2026, 4:10 p.m.