Triple
T19587993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lovells |
E470152
|
entity |
| Predicate | employeeCountBeforeMerger |
P23565
|
FINISHED |
| Object | over 3000 |
—
|
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: over 3000 | Statement: [Lovells, employeeCountBeforeMerger, over 3000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employeeCountBeforeMerger Context triple: [Lovells, employeeCountBeforeMerger, over 3000]
-
A.
marketPositionBeforeMerger
Indicates the competitive or strategic position an entity held in the market prior to a specific merger taking place.
-
B.
governingBodyBeforeMerger
Indicates that one entity functioned as the governing body of another entity prior to a merger event.
-
C.
affiliationBeforeMerger
Indicates that an entity was affiliated with another entity prior to a merger event involving one or both of them.
-
D.
staffSize
chosen
Indicates the number of staff members associated with an entity.
-
E.
originalNumberOfMembers
Indicates the initial total count of members in a group or organization before any changes such as additions or removals.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64052f61c81908bb49927d4246030 |
completed | April 20, 2026, 3:03 p.m. |
| PD | Predicate disambiguation | batch_69e514dbdb988190b55931a8138c73e7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.