Triple
T31706331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roorkee |
E809189
|
entity |
| Predicate | formerNameOfInstitutionLocatedHere |
P147693
|
FINISHED |
| Object | Thomason College of Civil Engineering |
—
|
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: Thomason College of Civil Engineering | Statement: [Roorkee, formerNameOfInstitutionLocatedHere, Thomason College of Civil Engineering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNameOfInstitutionLocatedHere Context triple: [Roorkee, formerNameOfInstitutionLocatedHere, Thomason College of Civil Engineering]
-
A.
parentInstitutionFormerName
Indicates that the parent institution of an entity previously operated under a different official name.
-
B.
formerInstitutionOnSite
chosen
Indicates that another institution previously occupied or operated on the same physical site as the current institution.
-
C.
historicalNameOfInstitution
Indicates that one institution is a former or historical name by which another institution was previously known.
-
D.
universityFormerName
Indicates that a university previously had a different official name before adopting its current one.
-
E.
hasFormerInstitutionName
Indicates that an institution was previously known by a different name.
- 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_69f348de914081909fc8edff56f34dbe |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff45793d5c81909dc503ad1f714ee2 |
completed | May 9, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69ff41cb0e088190a6e9b03cb20e5fad |
completed | May 9, 2026, 2:16 p.m. |
Created at: April 30, 2026, 11:14 p.m.