Triple
T17587872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heckman selection model |
E428370
|
entity |
| Predicate | typicalStep |
P128117
|
FINISHED |
| Object | estimate probit selection equation |
—
|
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: estimate probit selection equation | Statement: [Heckman selection model, typicalStep, estimate probit selection equation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalStep Context triple: [Heckman selection model, typicalStep, estimate probit selection equation]
-
A.
stepType
Indicates the specific kind or category of step an entity represents within a process or sequence.
-
B.
stepTakes
Indicates that one step directly follows or is taken after another step in a process or sequence.
-
C.
stepInRoutine
Indicates that an action or event occurs as an ordered step within a larger, structured routine or sequence of activities.
-
D.
stepCount
Indicates the number of discrete steps taken or required in a process, sequence, or movement.
-
E.
stepReturns
Indicates that a particular step in a process or workflow yields, outputs, or hands back a specified result or value.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e41bf08190963848f1597b6e9f |
completed | April 19, 2026, 5:36 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fff0348190b899a32da537eaca |
completed | April 18, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69e3bbb50b448190a59dd4be33c76db7 |
completed | April 18, 2026, 5:13 p.m. |
Created at: April 10, 2026, 5:51 a.m.