Triple
T3372329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lindbergh Field |
E70982
|
entity |
| Predicate | hasNumberOfTerminals |
P2957
|
FINISHED |
| Object | 2 |
—
|
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: 2 | Statement: [Lindbergh Field, hasNumberOfTerminals, 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfTerminals Context triple: [Lindbergh Field, hasNumberOfTerminals, 2]
-
A.
numberOfTerminals
chosen
Indicates the total count of terminal points or endpoints associated with an entity.
-
B.
hasSubTerminal
Indicates that an entity includes or is associated with a subordinate or lower-level terminal element within a hierarchical structure.
-
C.
hasNumberOfTerms
Indicates the quantity of distinct terms or elements associated with a given entity or expression.
-
D.
hasLeaves
Indicates that an entity possesses leaves as part of its structure or form.
-
E.
hasTerminusIn
Indicates that something (such as a route, line, or path) ends or has its final stopping point at a specified location.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2bc9bc881908b22edd631a1c110 |
completed | March 8, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ada433059881908e46f38cc5f40a32 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.